ClawAudit verdict
knowledge-engineering
RAG document chunking/slicing tool that runs local Python scripts to process documents; no network exfiltration or credential access, purely a local ETL pipeline.
⚠ 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 (6)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Node http/https module — low-level network access
QUICKSTART.md · code · require('http')
subprocess execution — runs system commands from Python
scripts/evaluate_retrieval.py · prose · downgraded · subprocess.run(
References sudo — requests elevated privileges
scripts/platform_detect.py · prose · downgraded · sudo
References child_process — can spawn system processes
scripts/slice_generator.py · prose · downgraded · child_process
Python os.environ.get — reads environment variable
scripts/platform_detect.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.