ai-agent-security agents

3 tagged ai-agent-security, measured the same way as everything else here.

agent-red-teamer

03

William2333ZZ/trustshell

Agent

Part of trustshell

Use this to security-test an AI AGENT (not ordinary app code) — prompt injection, memory poisoning, tool/action abuse, sandbox escape, channel injection, supply chain, exfiltration. It runs TrustShell's static-triage → dynamic-confirm loop and reports only exploit-validated findings. Authorized, disposable-environment…

1 1mo ago A 73 tokens original MIT