p-video

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path is belt app run pruna/p-video --input ..., where the user-supplied --input JSON (including free-form fields like prompt, and optionally image/audio URLs) is ingested into the LLM context; this is outsider-authored free text provided by someone other than the skill itself.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires running the npx installer ("npx skills add belt-sh/cli"), which causes code to be fetched from the npm registry (e.g. https://registry.npmjs.org/ for the belt-sh/cli package) and executed at install/runtime, so it is a runtime external dependency that executes remote code.