hyperframes

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

• Third-party content exposure detected (high risk: 0.70). The skill's docs explicitly instruct the agent to ingest external transcripts and audio data (e.g., using external transcription APIs like OpenAI/Groq in references/transcript-guide.md, importing transcripts via npx hyperframes transcribe and "fetch('audio-data.json')" in references/audio-reactive.md, and "Read the full transcript" in references/captions.md), meaning untrusted/user-generated third‑party content is fetched and must be read and interpreted to drive captioning, styling, and audio‑reactive animation decisions.