ClawAudit verdict
team-projects
The skill provides a multi-agent project management functionality with task boards, @-mention routing, WBS, and orchestrated team collaboration. It does not contain any malicious code or unusual capabilities.
⚠ 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 (5)
References agent configuration files
SKILL.md · code · AgentConfig
Instructs covert action — may act without user awareness
gateway-plugin/team-chat-drawer.ts · prose · downgraded · Silently
HTTP request to bare IP address — common in malicious payloads
scripts/gateway-handlers.js · prose · downgraded · http://127.0.0.1
Uses exec() — may execute shell commands
scripts/task-router.js · prose · downgraded · exec(
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
process_exec Is this flag fair?
Thanks — recorded.