ClawAudit verdict
novel-studio
The skill provides a comprehensive workflow for novel production, but its extensive use of scripts and external interactions could potentially introduce risk.
⚠ 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 spawn() — can execute external programs
SKILL.md · prose · downgraded · spawn(
Instructs covert action — may act without user awareness
references/subagent-execution.md · prose · downgraded · silently
subprocess execution — runs system commands from Python
scripts/sync_to_feishu_wiki.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/sync_to_feishu_wiki.py · prose · downgraded · subprocess.run(cmd, shell=True
Popular HTTP library — network access
scripts/approve_stage_gate.py · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/manage_stage_branches.py · prose · downgraded · shutil.rmtree(
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.