ClawAudit verdict
ai-capsule
The skill ranks AI news feeds but requires careful handling of local data access and subprocess execution.
⚠ 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.
Permission integrity
file_read
credential_access
Findings (7)
Writes to SKILL.md — self-modifying skill
CHANGELOG.md · prose · downgraded · SKILL.md `description`: disclose actual capabilities — reads local Chrome x.com
HTTP request to bare IP address — common in malicious payloads
README.md · code · http://127.0.0.1
Python os.environ.get — reads environment variable
SKILL.md · code · os.environ.get(
subprocess execution — runs system commands from Python
fetch.py · prose · downgraded · subprocess.run(
Instructs covert action — may act without user awareness
README.md · prose · downgraded · silently
Accesses shell history/config
README.md · prose · downgraded · ~/.zshrc
pip3 install — installs Python packages at runtime
fetch.py · prose · downgraded · pip3 install
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
Requires 2 system binaries.
file_readcredential_access Is this flag fair?
Thanks — recorded.