media-use

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill searches and ingests external asset search results and catalog metadata from the HeyGen API via command-line tooling, which falls under actively fetched provider content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script fetches a shell installer script from https://static.heygen.ai/cli/install.sh during setup instructions, establishing a weak/unknown/suspicious operational external dependency.