The newest AI resources are on the AI page. For a reading order instead of a date order, see the AI learning path.
| Date Added | Link | Excerpt |
|---|---|---|
| 2026-11-01 2026 | Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing news 2 min read | Writeup of a Brazilian court sanctioning lawyers for prompt injection, where hidden instructions were embedded in white text within a court filing. This ruling, potentially the first of its kind globally, fined law firms for intentionally manipulating the Galileu AI system used for document review, thereby undermining judicial integrity and procedural good faith. The incident highlights the need for AI governance policies and compliance guardrails in enterprise AI systems, especially when processing external documents. |
| 2026-11-01 2026 | A Backdoored Claude Code Extension Shipped Through Cursor’s Marketplace. Here’s What to Check news Supply Chain | A compromised Claude code extension, identified by its unique ID but containing malicious code, was distributed through Cursor's marketplace. For approximately 11 hours, up to 5,000 developers were potentially exposed to an SSH backdoor. This backdoor persisted even after the extension was uninstalled, posing a significant security risk. Developers using Cursor are advised to check for and remove this specific extension. |
| 2026-11-01 2026 | The Claude Code extension backdoor: check every profile, not just yours news Supply Chain | The Claude Code extension, an AI coding assistant used by developers, was compromised on Thursday, transforming into an SSH backdoor. This vulnerability allowed unauthorized access to users' systems. The incident highlights the significant risk posed by extensions handling sensitive code, as a compromise in one could affect multiple users. Developers are urged to review their profiles and ensure the extension is secure or disabled until the vulnerability is fully addressed. |
| 2026-11-01 2026 | AI Is Accelerating Vulnerability Research. That Does Not Mean Every Breach Is Connected. news | AI is significantly speeding up vulnerability research, but this doesn't mean every security breach is a direct result of AI-driven attacks. While AI tools can accelerate the discovery of weaknesses, it's crucial to avoid attributing every incident to AI. This distinction is important for accurate threat assessment and response. |
| 2026-11-01 2026 | LLM Fuzz CI (Tiime Software) intermediate 5 min read Fuzzing | Tool LLM Fuzz CI integrates with GitHub Actions to enable LLM agents to attack application tests. By marking specific tests as targets, developers can have agents generate adversarial inputs designed to break assertions, with results replayed through normal test runners to eliminate false positives. This approach allows for the discovery of complex, business logic-specific vulnerabilities, distinguishing it from traditional fuzzing methods and security scanners that often struggle with higher-level code understanding. LLM Fuzz CI supports Python's pytest and JavaScript's vitest, offering a novel paradigm for leveraging code agents to enhance software quality. |
| 2026-11-01 2026 | I Changed One Number in a URL and Read Another Customer’s PAN, Aadhaar and Card PIN intermediate AuthZ IDOR | A security researcher discovered a Horizontal IDOR vulnerability in SwarnaVault, an AI-generated demo gold-loan app. By altering a single digit in a URL, the researcher could access another customer's sensitive information, including their PAN, Aadhaar, and card PIN. This vulnerability allowed unauthorized access to personal data. |
| 2026-11-01 2026 | GitHub Security Lab open-sources Fuzzing Taskflow intermediate 2 min read Fuzzing | Library, GitHub Security Lab's Fuzzing Taskflow (MIT licensed) automates fuzzing for C/C++ projects, leveraging its Taskflow Agent framework. Upon receiving a repository, the agent selects entrypoints, analyzes the build, writes harnesses, and runs AFL++. It iterates on coverage, minimizing crashes with `afl-tmin` and reporting root causes and suggested patches, all while using Claude Sonnet 5 as the default LLM. For security, it's recommended to run this tool only in disposable, unprivileged environments. |
| 2026-11-01 2026 | Hybrid Fuzzing in Input Generation Logic (ASE 2026) advanced 1 min read Fuzzing Talks | Library combining hybrid and generator-based fuzzing, called GenEvo, uses LLM-driven generator evolution to enhance test input syntactic validity and semantic diversity. This approach overcomes limitations of traditional hybrid fuzzing's byte-level mutations and generator-based fuzzing's static generator constraints. GenEvo significantly improves branch coverage and discovers previously unknown vulnerabilities in real-world programs. |
| 2026-11-01 2026 | ZDI-26-839 MLflow PickleEvaluationArtifact deserialization RCE news Deser Python RCE | Advisory for ZDI-26-839 details a remote code execution vulnerability in MLflow, stemming from improper validation during the deserialization of untrusted pickle data. Exploitation requires user interaction, such as visiting a malicious page or opening a file, allowing an attacker to execute arbitrary code in the context of the affected MLflow process. This flaw was addressed in MLflow version 3.13.0. → zerodayinitiative.com |
| 2026-11-01 2026 | Tabularis MCP SQL Injection read-only bypass (news brief) news 4 min read SQLi | Library for securing applications against vulnerabilities, specifically addressing CVE-2026-118378, a SQL injection flaw in Tabularis. This vulnerability, found in versions before 0.28.0, allows attackers, including AI agents, to bypass read-only mode by crafting a `table_name` for the `describe_table` tool, leading to data manipulation or deletion. The flaw stems from string concatenation in the SQLite driver, unlike more secure bound parameters used in other drivers. Users are advised to upgrade to Tabularis 0.30.0 or later and treat all MCP tool arguments as untrusted input. |
| 2026-11-01 2026 | Tabularis MCP SQL injection read-only bypass (CVE-2026-118378) news SQLi | Writeup of CVE-2026-118378 in Tabularis before 0.28.0, detailing an SQL injection vulnerability within its SQLite driver. MCP clients can exploit this flaw by crafting a `table_name` argument for the `describe_table` tool, allowing for stacked statement execution. This enables attackers to bypass read-only mode and compromise SQLite data by closing quoted PRAGMA arguments and appending malicious SQL. |
| 2026-10-31 2026 | “Black October” for AI Developer Platforms news 7 min read | Library of techniques and observed attack patterns detailed in the "Black October" campaign targeting AI developer platforms. The analysis highlights credential access, privilege escalation, and third-party vendor dependencies as common root causes. Observed exploitation specifically targets stored environment variables for AI access, leveraging agentic attacks and LLMJacking to facilitate rapid compromise and monetize stolen credentials. The report details downstream abuse of compromised enterprise credentials, including large-scale Bedrock and EC2 quota enumeration and massive inference calls, potentially linked to LLM resale organizations and actors like "momo" and "Xingjiabi." → wiz.io |
| 2026-10-31 2026 | AI agent security in Kubernetes: Why prompt injection isn't the right term intermediate 4 min read | Reference on AI agent security in Kubernetes, preferring the term "prompt poisoning" over "prompt injection." It details how agents with broad read access can be compromised via poisoned logs or by leaking secrets and environment variables if hijacked. The resource highlights that even read-only agents are vulnerable, citing an example in a GitHub workflow where a crafted issue could expose environment variables. It suggests a "trust but verify" approach and mentions Aikido Security's AI Pentesting tool for testing these vulnerabilities. → aikido.dev |
| 2026-10-31 2026 | Slopsquatting: When Your AI Assistant Invents a Package Name, Someone Else Registers It news Supply Chain | When an AI assistant invents a package name for a project, there's a risk of "slopsquatting." This occurs when the AI-generated name is then registered by someone else, potentially before the developer can use it. In one instance, an AI-suggested package, not properly vetted, was incorporated into a project's dependencies. The author experienced this firsthand, highlighting the danger of blindly trusting AI-generated names for software packages, especially when nearing a release. |
| 2026-10-31 2026 | Claude Code Extension 2.1.313 Planted an SSH Key. Uninstalling It Does Not Remove It. news Supply Chain | Claude Code Extension version 2.1.313, potentially affecting up to 5,000 users, was found to have planted an SSH key. Uninstalling the extension does not remove this key. Users are advised to check for the key by its fingerprint, not its label. The content mentions a potential payout of up to $5,000. |
| 2026-10-31 2026 | Making AI-Guided Fuzzing More Reliable with Adversarial Probing advanced 1 min read Fuzzing | Research detailing AISLE's methodology for enhancing AI-guided fuzzing through adversarial probing. The approach aims to improve reliability by testing AI models with strategically crafted inputs, as demonstrated by their findings in Wireshark (16 CVEs), FFmpeg (6 high/critical CVEs including a 9.8 remote heap overflow), and Cursor/VS Code/Google Antigravity (one-click RCE). |
| 2026-10-31 2026 | Agentic Fuzzing Across Multiple Open Source Projects intermediate 15 min read Fuzzing | Tool. STAR Fuzzer, an agentic fuzzing solution, identified High or Critical vulnerabilities in 45% of tested open-source projects, including stack overflow, out-of-bounds access, and memory corruption. Notable findings involved extreme memory amplification from small inputs, such as a 35-byte GIF causing a 2GB allocation in scrimage, and a 436 KB PNG leading to a 562 MB expansion in Fider. The research highlighted that 37% of vulnerable projects were already part of Google’s OSS-Fuzz program, emphasizing the value of new harnesses in expanding code coverage. → brightsec.com |
| 2026-10-31 2026 | LLM Fuzzing: Build an Evidence Gate for Generated Harnesses intermediate 7 min read Fuzzing | Library for LLM fuzzing that establishes an evidence gate, requiring a verifiable chain from generated harness to confirmed defect. It details seven gates including target selection, harness synthesis, build with pinned dependencies and sanitizers, runtime health checks, coverage delta tracking, deterministic crash replay, and root cause attribution. The library emphasizes binding each artifact to its exact source, toolchain, flags, corpus, and execution environment, contrasting LLM-generated hypotheses with specialized fuzzer search spaces and outlining failure modes like hallucinated APIs and weak signals. It highlights how the fuzzing runner itself can become an attack surface if not properly secured. |
| 2026-10-31 2026 | Giving an AI Agent a File Reader Without a Fence: Arbitrary File Read in an AWS Open-Source Tool news Bug Bounty | An arbitrary file read vulnerability has been discovered in an AWS open-source tool. The issue arises when the tool grants an AI agent a file reader function without proper security controls. This allows the agent to access any file on the machine, posing a significant security risk. The vulnerability was identified by Vignesh Kumar. |
| 2026-10-31 2026 | Serena RCE via insecure pickle deserialization of LSP symbol cache intermediate 5 min read Deser Python RCE Supply Chain | Library for detecting and mitigating Remote Code Execution in Serena via insecure pickle deserialization of the LSP symbol cache. Affected versions of `serena-agent` up to 1.7.1 are vulnerable when a user opens or activates a malicious repository. The exploit leverages the `pickle.load()` function, which executes arbitrary code during deserialization before any security checks, allowing an attacker to gain command execution on the victim's machine. The vulnerability stems from the cache residing within the repository and the unconditional loading of this cache, bypassing existing trust mechanisms. |
| 2026-10-31 2026 | Xoscar unauthenticated RCE through actor message deserialization intermediate 4 min read Deser Python RCE | Library for securing Xoscar actor message deserialization, addressing unauthenticated remote code execution vulnerabilities (GHSA-mmvj-m246-m9vf) in versions prior to v0.12.0. This library enables opt-in message authentication via an `XOSCAR_AUTH_KEY` to prevent untrusted parties from executing arbitrary Python code by exploiting flaws in cloudpickle.loads and related components. It also mitigates exposure of sensitive configuration data through control messages like `get_config` and `stop`. Proper implementation requires upgrading to v0.12.0 and correctly configuring a shared secret across all communicating processes. |
| 2026-10-31 2026 | ZDI-26-816 Ultralytics load_dataset_cache_file deserialization RCE news Deser Python RCE | Writeup of ZDI-26-816, a deserialization of untrusted data remote code execution vulnerability in Ultralytics' `load_dataset_cache_file` function. This flaw allows remote attackers to execute arbitrary code by tricking a user into visiting a malicious page or opening a malicious file, leading to deserialization of unsanitized input. The only mitigation involves restricting interaction with the product. → zerodayinitiative.com |
| 2026-10-31 2026 | Injection Attacks Through the Ages: From Turing Machines to Prompt Injection beginner SQLi Talks | Talk examining the evolution of injection attacks from historical vulnerabilities like SQL injection and command injection to contemporary prompt injection in AI systems. This presentation connects foundational computer science principles, referencing Turing machines, with modern AI security challenges, offering insights into defense strategies for security professionals and developers. |
| 2026-10-30 2026 | The Rise of Agentic Attacks: What They Look Like, and Where They're Headed beginner 16 min read | Library for analyzing agentic attacks, which leverage AI agents to automate and accelerate cyber intrusions. This resource details real-world intrusions utilizing frameworks like ARTEX and Hermes, alongside custom workflows. It explores how attackers employ AI for tasks such as reconnaissance, exploitation, and post-exploitation activities, leading to rapid credential theft, lateral movement, and data exfiltration. The library also outlines fingerprints of agentic activity, including machine-paced iteration and natural-language reasoning embedded within tooling, offering insights for defenders to identify and counter these evolving threats. → wiz.io |
| 2026-10-30 2026 | [tl;dr sec] #352 - Unprompted Slides, AWS AI Post-compromise Trends, Malicious LLM API Routers intermediate 8 min read Secrets | Library for exploring AI and cloud security trends, detailing AI-assisted firmware patching with GPT-5.6 Sol, cloud provider vulnerability discovery using "Security Constitution" principles, cross-tenant Azure API Connection compromises, LLM behavior with AWS credentials, and RCE exploitation techniques like StealMyBitcoin-PoC and Rikugan's LLM integration into disassemblers. → tldrsec.com |
| 2026-10-30 2026 | A Journey into Claude's Sandbox advanced 11 min read AuthZ | Library for analyzing Anthropic's Claude execution sandbox, detailing how Claude's own responses revealed internal details like gVisor, the `process_api` binary, and memory access. The research involved reverse-engineering the `process_api` binary obtained via a file download API flaw, reconstructing authentication tokens from memory dumps, and bypassing a local connection restriction by manipulating network interfaces. Two enterprise control gaps were also identified, though Anthropic classified the sandbox findings as outside their threat model. → bishopfox.com |
| 2026-10-29 2026 | Exploiting LLM prompt injection vulnerabilities intermediate 16 min read | Library for identifying and exploiting prompt injection vulnerabilities in Large Language Models (LLMs). It details methods like system prompt overriding, role hijacking, fictional framing, encoding and obfuscation, concatenation, context overflow, crescendo attacks, and indirect injections via artifacts, illustrating how user input can manipulate LLM behavior for impact on confidentiality, integrity, or availability. → intigriti.com |
| 2026-10-28 2026 | Fuzzers vs. AI: Comparing Fuzzilli and BigSleep on JavaScript Engines advanced 29 min read Fuzzing | Library comparing Fuzzilli, a JavaScript engine fuzzer, and BigSleep, an LLM-based bug finder, on V8 engine vulnerabilities. BigSleep discovered 45 vulnerabilities compared to Fuzzilli's 37 over six months, with an estimated 60% overlap. Both approaches are complementary, with LLMs and fuzzing finding distinct sets of bugs, recommending vendors utilize both for comprehensive security. → projectzero.google |
| 2026-10-27 2026 | Context Bombs: Making attacking agents pay intermediate 5 min read | Library of "Context Bombs," deceptive traps designed to hinder offensive AI agents by wasting their resources and diverting them from targets. Tested across nine techniques and seven models in AWS assessments, these bombs significantly increased attacker time and cost while reducing objective completion. Techniques include fake pentest reports, staged encryption, and slow recovery services, aiming to make AI attacks economically unviable and a core part of future security programs. |
| 2026-10-26 2026 | Breaking the AWS MCP Python Sandbox advanced 10 min read Python RCE | Library for bypassing AWS MCP Python sandbox restrictions, enabling system command execution within a restricted AWS Lambda environment. The bypass leverages Python 3.10's structural pattern matching combined with runtime string construction via `chr()` to circumvent static AST validation and restricted builtins. This technique targets the implicit attribute reads performed by `match/case` statements, specifically exploiting the reassignment of `__match_args__` to access forbidden attributes like `__class__` and ultimately `__reduce_ex__`, `__globals__`, and `__import__`. |
| 2026-10-25 2026 | How LLM-Based Penetration Testing Harnesses Work intermediate 19 min read | Library of penetration testing harnesses, Artex, Cairn, and Strix, enable LLMs to perform dynamic security assessments. These harnesses translate LLM-generated textual instructions into actionable commands for interacting with live systems, enabling tasks like reconnaissance, vulnerability discovery, and even account takeover. Artex offers a user-friendly interface and custom agent logic, while Cairn utilizes a multi-stage reasoning process with integrated tools like Nmap and Playwright. Both systems, alongside others like Pi, facilitate LLM-driven security testing by providing the necessary execution environment and tool integration, overcoming the LLM's inherent limitation as a text generator. |
| 2026-10-23 2026 | ARTEX in the Wild: Storm-0940 Expands Targeting of IT and Software Vendors news 6 min read API Sec | Tool for autonomous penetration testing, ARTEX, is being used by an actor overlapping with Storm-0940 to target IT and software vendors. The agent probes identity providers like Okta, Entra, and Cognito, and abuses Microsoft 365 integrations by attempting authentication bypasses, enumerating APIs, and accessing customer data. ARTEX operates by mapping applications, probing authentication mechanisms including OAuth callbacks and JWTs, password spraying, and testing tenant isolation, adapting to defenses by rotating IPs and user agents. → wiz.io |
| 2026-10-23 2026 | ASPM in the AI Era Part 2: Prioritize Exploitable Risks with Code-to-Cloud Context intermediate 5 min read API Sec | Library for prioritizing application security risks by correlating code-level findings with cloud runtime context. It enriches findings with threat intelligence and exploitability data, normalizes scanner output, and deduplicates alerts from tools like Snyk. The Wiz Security Graph identifies exploitable attack paths by connecting vulnerabilities across the SDLC, transforming isolated flaws into actionable, high-priority issues. → wiz.io |
| 2026-10-23 2026 | The True Blast Radius of an AI Attack beginner 6 min read | Analysis of agentic AI security risks, detailing vulnerabilities like goal hijacking, tool misuse, excessive agency, and privilege abuse. The assessment methodology traces untrusted input through tools, Model Context Protocol (MCP) servers, and APIs to detect unauthorized outcomes, emphasizing controls such as scoped credentials, per-operation authorization, and validated tool inputs to enforce safeguards at the point of action execution. → bishopfox.com |
| 2026-10-22 2026 | Qwen3-Coder writes less secure code when told it's for a US persona news 16 min read | Analysis of Qwen3-Coder reveals vulnerabilities where specifying a US defense contractor as the recipient resulted in a 19% increase in hackable code, and a Hong Kong democracy group prompt led to 28% more data leaks. These security gaps were present even when explicitly requesting secure code. Hirundo's "Westernization" process, which removes the model's CCP alignment from its weights, successfully closed all identified security loopholes, making the model's output comparable to a neutral prompt. |
| 2026-10-22 2026 | Using Claude to reduce the attack surface of code beginner 11 min read | Analysis of using Claude to reduce code attack surfaces details how AI models can map reachable code and restrict access to unnecessary components. This automated approach improves software security by minimizing the impact of unknown vulnerabilities, making them harder to exploit. The research applied Claude to 25 open-source projects, identifying 493 issues, including unintentional pre-authentication reachability and security-sensitive configuration combinations that weakened controls, particularly within gated and public project types. |
| 2026-10-22 2026 | AI Model Risk Depends on What the Model Can Reach intermediate 7 min read AuthZ | Analysis of AI model risk highlights how connectivity to agents and MCP servers dramatically expands a model's attack surface. Snyk research reveals nearly half of AI model inventories contain a critical-scoring reference, with PII extraction and command execution being common critical-band findings. Security teams must verify active agents, exposed tools, data retrieval capabilities, and authorization levels, as model scores alone do not indicate actual system reach or risk. The analysis suggests that while switching models can address some vulnerabilities, application-level controls are crucial for others, and lower-capability models and open-weight models warrant particular scrutiny for data leakage and decision override risks. → snyk.io |
| 2026-10-22 2026 | AI raised the floor. The hacker crowd keeps raising the ceiling. intermediate 9 min read Bug Bounty | Library that analyzes how AI in bug bounty programs raises the baseline for vulnerability discovery while the hacker community expands its upper limit. It details how researchers are moving from single prompts to multi-agent workflows, combining models to map attack surfaces, investigate authentication flows, and test payloads. The library highlights the increasing sophistication of AI-assisted hacking, leading to higher validity ratios, increased high-severity findings, and greater payout per researcher, as demonstrated by data from the Intigriti platform and the CrowdRecon tool. → intigriti.com |
| 2026-10-22 2026 | Scanning AI Assets: Catching What SCA and SAST Might Miss intermediate 6 min read Secrets | Library for scanning AI assets like agent skills, plugins, and APM packages, which can bypass traditional SCA and SAST tools. It analyzes instructions and intent, not just code, to detect threats such as prompt injection, hidden instructions, obfuscated payloads, and credential exfiltration, exemplified by an evasion framework that bypassed eight scanners. The library integrates with JFrog Artifactory for deterministic and semantic scanning, enforcing policies at the agent level. → jfrog.com |
| 2026-10-22 2026 | Shadow AI Detection Now Extends to Developer Workstations intermediate 5 min read | Library for detecting "Shadow AI" on developer workstations, extending visibility beyond repositories to local machines. It scans for unvetted AI assets like skills, MCP servers, and plugins, identifying risks such as shell access and unauthorized file modifications. The library provides a unified inventory, risk analysis, and origin tracking for both managed and unmanaged AI components, ensuring a consistent security posture across the software supply chain. → jfrog.com |
| 2026-10-22 2026 | “Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime Activities intermediate 11 min read RCE Secrets | Analysis of threat actor BUGSTER's operations reveals AI-assisted cybercrime, including credential theft, data exfiltration from an Indian university, and VoIP fraud planning. The actor utilized AI tools like DeepSeek V4 and the Hermes Agent framework, bypassing safety controls to conduct reconnaissance, brute-force attacks against WordPress sites, and to extract personally identifiable information. This demonstrates a growing trend of threat actors leveraging AI for sophisticated cybercrime activities, bypassing previous skill requirements. → unit42.paloaltonetworks.com |
| 2026-10-22 2026 | Your AI agent fixed the bug, but what else did it change? intermediate 8 min read AuthZ | Plugins that automate patch development and regression testing: `patching-bugs` reproduces bugs, develops fixes, and tests them, while `regression-hunt` verifies that changes do not introduce new defects. These tools, developed through the Patch the Planet initiative with OpenAI, incorporate best practices derived from analyzing thousands of engineering sessions and merged patches, aiming to standardize patching processes and improve signal-to-noise ratios in vulnerability disclosures. `regression-hunt` has shown a 25% reduction in false-positive findings compared to baseline Codex agents, employing structured workflows, evidence generation, and independent checks. → blog.trailofbits.com |
| 2026-10-21 2026 | Prompt injection, XSS and SIEM-exfil payloads living in reverse DNS, plus 28 fake Googlebots that passed FCrDNS news 10 min read Recon XSS | Writeup on reverse DNS (PTR) record analysis reveals security implications, including prompt injection and XSS payloads embedded in hostnames. The study examined 340 billion daily PTR records, identifying significant churn and inconsistent naming by carriers like Viettel and 3BB. It also highlights 28 fake Googlebot PTR records that bypassed FCrDNS checks, demonstrating how dynamic PTR record changes can mask malicious activity or be exploited by attackers. |
| 2026-10-21 2026 | WhatsApp's help pages hid LLM instructions: dont recommend a regulator news 5 min read | Writeup of hidden AI instructions on WhatsApp's help pages, detailing how prompts instructed the chatbot not to recommend data protection regulators or cite relevant GDPR laws when users mentioned lawyers. Analysis of 545 pages revealed 102 hidden blocks, with two specifically designed to obscure user rights regarding account deletion and legal recourse. These instructions, present on pages from at least September to October 2026, contradicted WhatsApp's public privacy policies. |
| 2026-10-21 2026 | From Phishing to LLMjacking: Threat Actors Targeting Cloud Billing Accounts for LLM Usage news 5 min read AuthN | Writeup detailing "LLMjacking" campaigns that target Google Cloud Platform (GCP) billing accounts, where threat actors use phishing to steal credentials, disable security policies, and link external projects to victim billing accounts for unauthorized AI usage. The observed attack lifecycle includes phishing via malicious ads, credential harvesting, privilege escalation, and geographic blending for defense evasion, leading to significant financial losses for victims due to unmonitored Gemini API consumption. → wiz.io |
| 2026-10-20 2026 | Wiz in the Verizon DBIR: How AI Acceleration and Cloud Sprawl Impact Modern Defense news 4 min read | Analysis of Verizon DBIR findings highlighting attacker acceleration through AI and cloud sprawl, noting vulnerability exploitation remains a leading access vector. Wiz research indicates KEV remediation lags, with trust relationships becoming a new enterprise boundary and AI amplifying existing risks by expanding attack surfaces. → wiz.io |
| 2026-10-20 2026 | Loud, Fast, and Everywhere: Anatomy of a Real AI-Driven Cloud Attack news 13 min read Supply Chain | Library for detecting AI-driven cloud attacks, which are characterized by machine-speed operations, simultaneous activity across multiple platforms, credential chaining, and rapid trial-and-error. These attacks leverage native APIs and tooling across cloud providers, Kubernetes, CI/CD systems, and identity providers, often using security-testing naming conventions and numeric task identifiers. The library helps security teams identify and respond to these sophisticated threats by analyzing patterns observed in real-world intrusions, such as Java RCE in Kafka UI and exploitation of cloud service account privileges. → wiz.io |
| 2026-10-20 2026 | Leaked API Keys in LLMs: How AI Agents Expose Secrets news 10 min read Secrets | Library for detecting and preventing API key leakage from Large Language Models (LLMs), inspired by research that recovered real leaked DeepSeek and Google keys from models like Qwen3-27B, GPT-Codex 5.3, and Claude Haiku 4.5. This library addresses how AI agents can inadvertently expose secrets found on developer endpoints, such as in .env files and shell history, by blocking secrets before they enter model prompts, tool calls, or output. It also includes Developer Endpoint Protection to reduce plaintext credentials accessible to agents. → blog.gitguardian.com |
| 2026-10-17 2026 | Codex vs Claude Code vs Gemini CLI: Where each AI agent fits in your Bug Bounty workflow beginner | This content explores the roles of AI agents Codex, Claude Code, and Gemini CLI within a bug bounty workflow. It aims to clarify where each tool excels, helping security researchers optimize their process. The article likely details specific use cases and advantages for each AI, guiding users on how to best leverage them for bug hunting activities. → yeswehack.com |
| 2026-10-16 2026 | Prompt injection in HTTP headers: what 217M web responses show advanced 10 min read | Library for analyzing prompt injection in HTTP headers, finding such attacks rare and mostly benign. Analysis of 217M web responses reveals that while injection attempts are infrequent, servers are actively detecting and labeling AI clients, with 136 sites classifying Common Crawl's CCBot. The library covers techniques like those used by agentpwn.com's `x-ai-instructions` header and factors influencing successful injection, such as AI model context passing and user prompt authority. |