yt

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and API examples explicitly call transcriptapi.com endpoints (e.g., /api/v2/youtube/transcript and /api/v2/youtube/search) to fetch public YouTube transcripts and search results—user-generated, untrusted content the agent is expected to read and could materially influence its behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime calls to https://transcriptapi.com (e.g., /api/v2/youtube/transcript and /api/auth) to fetch transcript/search data which is injected into the agent's context to generate responses, so external content from that URL can directly influence prompts/outputs.