Caveat verdict
heygen-skills
HeyGen video creation skill using the official HeyGen API via MCP or CLI; file access is explicitly scoped to avatar identity files and a local video log, with remote uploads only when user explicitly provides assets — behavior matches stated video generation purpose.
⚠ 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)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
INSTALL_FOR_AGENTS.md · code · curl -fsSL https://static.heygen.ai/cli/install.sh | bash
Pipe to bash — executes piped content as shell commands
INSTALL_FOR_AGENTS.md · code · | bash
<script> tag in markdown — potential code injection
references/avatar-discovery.md · code · <script>
Accesses shell history/config
INSTALL_FOR_AGENTS.md · code · ~/.zshrc
References webhook/callback URL
SKILL.md · code · callback_url
References agent configuration files
CLAUDE.md · code · CLAUDE.md
Popular HTTP library — network access
references/prompt-craft.md · code · got
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
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
Requires 1 environment variable. (1 sensitive: HEYGEN_API_KEY).
network_in Is this flag fair?
Thanks — recorded.