ClawAudit verdict

lobster-novel

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

A local novel-writing pipeline tool that orchestrates Python scripts for text generation, continuity tracking, and export; the SenseNova API call is a documented, user-initiated LLM writing feature consistent with the skill's stated 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.

63
security
100
transparency
90
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

write_ch1.py · prose · downgraded · API_KEY="): os.environ[

Pattern match medium

subprocess execution — runs system commands from Python

learnings/novel_lesson_bridge.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

batch_vol1.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

batch_vol1.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

batch_vol1.py · prose · downgraded · got

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API