hyperframes

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

• Third-party content exposure detected (high risk: 0.80). The skill's caption/transcript workflow (references/captions.md and references/transcript-guide.md) explicitly instructs importing and reading transcripts from external sources and APIs (e.g., SRT/VTT from YouTube, OpenAI/Groq transcription outputs and curl examples), which the agent must parse and use to choose caption style and drive animations—i.e., untrusted, third‑party text is ingested and can materially influence next actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's sub-composition template loads and executes remote JavaScript at runtime from https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js (GSAP), which the skill relies on for timeline/animation construction, so this URL fetches and executes required remote code at runtime.