Caveat verdict
security-analyst
Comprehensive security analysis and penetration testing skill that coordinates agents for vulnerability scanning, threat modeling, and compliance mapping; all operations are analytical/read-oriented against the local codebase with no evidence of data exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (7)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Accesses sensitive system files
references/prompts/config-infrastructure.md · prose · downgraded · /etc/passwd
Opens WebSocket connection
SKILL.md · code · WebSocket
Accesses cloud provider credentials
references/plugins/aws-gcp-azure.md · prose · downgraded · ~/.aws
Instructs covert action — may act without user awareness
references/plugins/owasp-infra-top10.md · prose · downgraded · silently
References agent configuration files
assets/templates/fix-plan.md · prose · downgraded · CLAUDE.md
Popular HTTP library — network access
references/prompts/git-history-ssrf.md · prose · downgraded · axios
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.