product-launch-video

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

• Third-party content exposure detected (medium risk: 0.30). The workflow consumes an external user's input script and captured website content (free text and structure via capture and user_script.txt), which are ingested directly by the LLM and the project's orchestration scripts.

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

• Potentially malicious external URL detected (high risk: 0.70). The instruction mandates updating the skill via npx hyperframes skills update product-launch-video, which executes an external command fetching remote content from GitHub at runtime.