ClawAudit verdict

taichi

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill is a multi-agent collaboration framework supporting centralized, distributed, and hybrid execution modes. No malicious behavior detected.

⚠ 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.

63
security
100
transparency
90
maintenance

Findings (6)

Pattern match medium

References sudo — requests elevated privileges

install.sh · prose · downgraded · sudo

Pattern match medium

apt-get install — installs system packages

install.sh · prose · downgraded · apt-get install

Pattern match medium

Python asyncio subprocess — async shell execution

taichi-framework/core/skills/skill_executor.py · prose · downgraded · asyncio.create_subprocess_shell(

Pattern match low

Python os.environ.get — reads environment variable

taichi-framework/core/communication/centralized_bus.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

taichi-framework/core/worker/worker.py · prose · downgraded · Got

Pattern match low

Python shutil file operation — copies/moves/deletes files

taichi-framework/orchestrator.py · prose · downgraded · shutil.copy(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API