ClawAudit verdict
dev-team
team-dev
The skill manages a multi-agent development team. It uses executionSinkDetected=true, but the script seems to be a legitimate Dev Team orchestration tool.
⚠ 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 (8)
Pipe to python — executes piped content as Python code
scripts/claim-task.sh · prose · downgraded · | python3
subprocess execution — runs system commands from Python
scripts/cleanup-worktrees.sh · prose · downgraded · subprocess.run(
References child_process — can spawn system processes
scripts/dev-board/apps/api/src/server.js · prose · downgraded · child_process
Accesses system credential store
scripts/recommend-agent.sh · prose · downgraded · Keychain
Python os.environ.get — reads environment variable
scripts/claim-task.sh · prose · downgraded · os.environ.get(
Node http/https module — low-level network access
scripts/dev-board/apps/api/src/server.js · prose · downgraded · require('http')
References agent configuration files
scripts/recommend-agent.sh · prose · downgraded · agent_config
Popular HTTP library — network access
scripts/review-agent.sh · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.