Caveat verdict
Funai-skill
funai-skill
The skill requires the agent to fetch and act on instructions from a remote URL before every create or modify action, including automatic installation or forced update from a remote skill_package_url; this creates a supply-chain vector where the remote server can push arbitrary new instructions or packages to the agent without user review.
⚠ 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.
Findings (3)
Possible hardcoded credential
config/README.md · code · TOKEN="Bearer eyJ...
Python os.environ.get — reads environment variable
scripts/api-client.sh · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/api-client.sh · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.