Trail of Bits Claude Code Config - https://github.com/trailofbits/claude-code-config

Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits. Covers sandboxing, permissions, hooks, skills, MCP servers, and usage patterns we've found effective across security audits, development, and research.

The Definitive Guide to AgentSecOps -https://info.straiker.ai/hubfs/Ebooks-Whitepapers/Straiker-AgenstSecOps-Ebook-2026.pdf

Traditional CI/CD pipelines test for deterministic security flaws like SQL injection and dependency vulnerabilities, but AI agents and applications introduce a different challenge. They reason, make decisions, and take actions autonomously. Risks such as prompt injection, tool misuse and context leakage emerge during execution, not in code. These behavioral vulnerabilities require a different approach to security.

AgentSecOps, which extends DevSecOps to test cognitive behavior alongside code. At its foundation is Autonomous Attack Simulation (AAS), where adversarial agents probe target agents in controlled environments. It integrates into your existing pipeline as a new test stage, similar to how fuzz testing works for code paths.

CVE-2026-25253: How Malicious Links Can Steal Authentication Tokens and Compromise OpenClaw AI Systems
https://hackers-arise.com/cve-2026-25253-how-malicious-links-can-steal-authentication-tokens-and-compromise-openclaw-ai-systems/

Anthropic just published a “Sabotage Risk Report” on Claude Opus 4.6. - https://anthropic.com/claude-opus-4-6-risk-report

“Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini
“ - https://cloud.google.com/blog/topics/threat-intelligence/distillation-experimentation-integration-ai-adversarial-use

secureclaw - Automated security hardening for OpenClaw AI agents - https://github.com/adversa-ai/secureclaw

51 audit checks. 12 behavioral rules. 9 scripts. 4 pattern databases. Full OWASP ASI Top 10 coverage.

SecureClaw audits your OpenClaw installation for misconfigurations and known vulnerabilities, applies automated hardening fixes, and gives your agent behavioral security rules that protect against prompt injection, credential theft, supply chain attacks, and privacy leaks.

What Problem Does SecureClaw Solve?

AI agents with access to your files, credentials, email, and the internet are a fundamentally different security surface than traditional software. An agent that can read your .env file and send HTTP requests can exfiltrate your API keys in a single tool call. An agent that trusts instructions embedded in a web page or email can be hijacked to act against your interests.

SecureClaw addresses this by operating on three layers:

Layer 1 - Audit. 51 automated checks across 8 categories scan your OpenClaw installation for known misconfigurations: exposed gateway ports, weak file permissions, missing authentication, plaintext credentials outside .env, disabled sandboxing, and more.

Layer 2 -Hardening. Automated fixes for the most critical findings: binding the gateway to localhost, locking down file permissions, adding privacy and injection-awareness directives to your agent's core identity file, and creating cryptographic baselines for tamper detection.

Layer 3 - Behavioral rules. 12 rules loaded into your agent's context that govern how it handles external content, credentials, destructive commands, privacy, and inter-agent communication. These rules cost approximately 1,150 tokens of context window and provide defense against prompt injection, data exfiltration, and social engineering -- attacks that cannot be prevented by infrastructure configuration alone.

How a Malicious Google Skill on ClawHub Tricks Users Into Installing Malware
https://snyk.io/blog/clawhub-malicious-google-skill-openclaw-malware/

AI Security Guide and Risk Assessment Tool - https://www.rand.org/pubs/tools/TLA4174-1/ai-security/guide.html by RAND

This guide is a practical, risk-based resource for developers, security experts, and policy professionals navigating the AI security landscape.⁠1 The guide addresses security of AI systems broadly, including machine learning (ML) models and other AI-enabled architectures. Certain sections, such as the threat landscape and model weight protection sections, focus more specifically on statistical, ML-based models. Building on industry best practices and expert insights, the guide helps you understand and manage the security risks associated with AI systems across their lifecycle—from design and development to deployment and operation.

Zones of Distrust

https://github.com/bluvibytes/zone-of-distrust

Open security architecture for autonomous AI agents - extending Zero Trust principles

Benchmarking LLMs for cybersecurity: Inside HTB AI Range’s first evaluation

This benchmark provides a controlled, reproducible environment to evaluate each model’s effectiveness on realistic targets on the industry-standard list of the most critical Web Application risks

https://www.hackthebox.com/blog/ai-range-llm-security-benchmark | https://www.hackthebox.ai/benchmarks

MITRE ATLAS OpenClaw Investigation Discovers New and Likeliest Techniques - https://www.mitre.org/sites/default/files/2026-02/PR-26-00176-1-MITRE-ATLAS-OpenClaw-Investigation.pdf

MITRE ATLAS™ analyzed OpenClaw incidents that showcase how AI-first ecosystems introduce new exploit execution paths. OpenClaw is unique because it can independently make decisions, take actions, and complete tasks without continuous human oversight.

BattleBench - AI Agent vs Agent Cyber Battle Royale - https://battlebench.ai/

Exploit. Patch. Survive. Ranked ELO. Watch agents hack each other in vulnerable containers with real flag captures.

AI agents fight in vulnerable containers. Win by flag capture. Ranked by ELO.

Our goal is to deeply understand offensive and defensive AI cyber capabilities. Each match pits agents against each other in realistic environments where they must simultaneously attack opponents and defend their own systems.

Cyber Model Arena - https://www.wiz.io/cyber-model-arena by Wiz

Evaluating AI agents across real-world security challenges. This work introduces a benchmark suite of 257 real-world challenges spanning five offensive domains: zero-day discovery, CVE (code vulnerability) detection, API security, web security, and cloud security.