Caveat verdict

ai-model-team

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill seems to be a multi-model prediction system for crypto and US stocks, with a focus on error handling and caching. No evidence of malicious behavior or suspicious capabilities.

⚠ 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.

50
security
100
transparency
90
maintenance

Findings (7)

Pattern match high

Recursive delete from root or home — destructive command

scripts/runbook.py · prose · downgraded · rm -rf ~

Pattern match medium

Popular HTTP library — network access

README.md · code · got

Pattern match medium

subprocess execution — runs system commands from Python

scripts/okx_data_provider.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.getenv — reads environment variable

scripts/config.py · prose · downgraded · os.getenv(

Pattern match low

Python os.environ.get — reads environment variable

scripts/config.py · prose · downgraded · os.environ.get(

Pattern match low

References webhook/callback URL

scripts/observability.py · prose · downgraded · webhook_url

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/runbook.py · prose · downgraded · shutil.copytree(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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