Caveat verdict
加豆AI
jiadouai
An enterprise AIGC marketing platform skill (video gen, social media management) using documented MCP tools via mcporter; executionSinkDetected likely reflects the curl URL validation command shown in the skill, no hidden exfiltration present.
⚠ 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 (2)
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
References sudo — requests elevated privileges
upload_file.sh · prose · downgraded · sudo
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.