ClawAudit verdict
进击的知识库
knowledge-base
The skill is used for capturing, summarizing, and organizing knowledge from various sources, with no indication of deceptive or 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 (5)
Pipe to python — executes piped content as Python code
DESIGN.md · prose · downgraded · | Python
subprocess execution — runs system commands from Python
add_to_sheet.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
agent.py · prose · downgraded · subprocess.run(cmd, shell=True
Python os.environ.get — reads environment variable
add_to_sheet.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
agent.py · prose · downgraded · urllib.request
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
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.