Caveat verdict
heygen
video-agent
This is a clearly labeled deprecated HeyGen skill wrapping documented v1/v2 endpoints or MCP tools with an API key, performing entirely expected video generation tasks with no suspicious behavior.
⚠ 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 (8)
Possible hardcoded credential
references/authentication.md · code · API_KEY="your-api-key-here
Accesses sensitive environment variables
references/assets.md · code · process.env.HEYGEN_API_KEY
POSTs data to external URL
references/assets.md · code · .post(
"https://
Popular HTTP library — network access
references/authentication.md · code · axios
References webhook/callback URL
references/templates.md · code · callback_url
References agent configuration files
references/video-agent.md · code · AgentConfig
References tunneling service
references/webhooks.md · code · ngrok
Makes HTTP request to external URL
references/assets.md · code · fetch("https://
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
Requires 1 environment variable. (1 sensitive: HEYGEN_API_KEY).
Is this flag fair?
Thanks — recorded.