ClawAudit verdict
book-writer
This AI-assisted book writing skill reads OPENAI_API_KEY and GOOGLE_API_KEY from environment variables to generate content and search for materials, both clearly consistent with the stated writing-assistance purpose.
⚠ 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)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_openai_api_key
subprocess execution — runs system commands from Python
scripts/install_dependencies.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/install_dependencies.py · prose · downgraded · subprocess.run(cmd, shell=True
Accesses shell history/config
scripts/install_dependencies.py · prose · downgraded · ~/.zshrc
Python os.environ.get — reads environment variable
scripts/book_writer.py · prose · downgraded · os.environ.get(
importlib.import_module — dynamic module loading
scripts/test_installation.py · prose · downgraded · importlib.import_module(
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.
credential_access Is this flag fair?
Thanks — recorded.