ClawAudit verdict
web-fetcher
The skill fetches web content from various platforms, with no clear 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 (6)
Uses eval() — can execute arbitrary code
lib/article.py · prose · downgraded · eval(
subprocess execution — runs system commands from Python
lib/article.py · prose · downgraded · subprocess.run(
Uses exec() — may execute shell commands
lib/readability.js · prose · downgraded · exec(
Python urllib.request — network access
lib/article.py · prose · downgraded · urllib.request
Popular HTTP library — network access
lib/readability.js · prose · downgraded · got
String.fromCharCode — can build strings to evade detection
lib/readability.js · prose · downgraded · String.fromCharCode
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.