ai-agent-framework-attack
A reusable agent skill published by brucesongs/kali-claw.
How do I install this agent skill?
npx skills add https://github.com/brucesongs/kali-claw --skill ai-agent-framework-attackIs this agent skill safe to install?
- Gen Agent Trust Hubfail
This skill is a comprehensive offensive security (red-teaming) resource focused on the attack surface of AI agent frameworks like LangChain, CrewAI, and AutoGen. While it contains numerous examples of prompt injection, data exfiltration, and remote code execution, these are presented as educational payloads and test cases for security research purposes. The malicious URLs detected by automated scanners are documentation placeholders using the reserved 'example.com' domain. No active malicious behavior was identified within the skill's own code or operational structure.
- Socketwarn
2 alerts: gptSecurity
- Snykpass
Risk: LOW · No issues
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/brucesongs/kali-claw/ai-agent-framework-attack">View ai-agent-framework-attack on skillZs</a>