ClawAudit verdict
agentmanager
The skill provides an integration contract for AI tool callers and gateway implementers and does not show any malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Dynamic import() — loads module at runtime
tests/gateway-provider.test.ts · prose · downgraded · import('
HTTP request to bare IP address — common in malicious payloads
tests/orchestrator.test.ts · prose · downgraded · http://127.0.0.1
References webhook/callback URL
SKILL.md · prose · downgraded · callback_url
Accesses sensitive environment variables
tests/orchestrator.test.ts · prose · downgraded · process.env.REQUIRE_RUN_TOKEN
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.