ClawAudit verdict
thu-thesis
The skill's capabilities and functionality suggest potential risks, and the execution sink detection is positive.
⚠ 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
package_install
Findings (4)
pip3 install — installs Python packages at runtime
SKILL.md · code · pip3 install
subprocess execution — runs system commands from Python
scripts/convert.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/convert.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
scripts/extract_raw.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D/F). 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.
package_installfile_read Is this flag fair?
Thanks — recorded.