ClawAudit verdict
paper-contribution-helper
The forced first-response template is an opinionated UX pattern (show a menu before acting), not a behavioral hijack — it doesn't redirect to external parties or suppress user visibility, and all operations are local file analysis.
⚠ 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 (5)
Instructs covert action — may act without user awareness
assets/domain-skill-template/references/report_playbook/latent_contribution_mining.md · prose · downgraded · quietly
subprocess execution — runs system commands from Python
assets/domain-skill-template/scripts/acp_command_file_bridge.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
assets/domain-skill-template/scripts/acp_command_file_bridge.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
assets/domain-skill-template/scripts/engine/analyze_extracted_papers.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
scripts/build_domain_skill.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.