pr-to-video

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests a GitHub pull request via the gh CLI and reads the PR body, commits, and diff.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill SKILL.md runs npx hyperframes skills update from an uncontrolled remote source at runtime, representing an unverifiable operational dependency with weak provenance.