transcriptapi

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and API endpoints (e.g., GET /api/v2/youtube/transcript and the "Tips" section that says "When user shares YouTube URL ... fetch transcript and summarize key points") show the agent will fetch and consume publicly posted YouTube transcripts/descriptions (user-generated content) as part of its workflow, which could carry untrusted instructions that influence subsequent actions.