Caveat verdict

content-engine

qianxun-content-engine

🟢 Trusted

No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

This Chinese content engine skill deconstructs social media posts and generates content using Ofox/LLM APIs; file_write is for local output files and the architecture is transparent with no suspicious data exfiltration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

transparency

maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Findings (6)

Pattern match high

Possible hardcoded credential

scripts/content_engine/client.py · prose · downgraded · TOKEN='你的_token

Pattern match medium

subprocess execution — runs system commands from Python

scripts/content_engine/lookup.py · prose · downgraded · subprocess.run(

Pattern match medium

References sudo — requests elevated privileges

scripts/content_engine/preflight.py · prose · downgraded · sudo

Pattern match low

Python urllib.request — network access

scripts/content_engine/client.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/content_engine/client.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

scripts/content_engine/video.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.

file_write

Is this flag fair?

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