youtube-search
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill calls TranscriptAPI endpoints (e.g., https://transcriptapi.com/api/v2/youtube/search and /transcript) to retrieve YouTube videos, channel data, and full transcripts — public, user-generated content that the agent is expected to read and interpret, which can carry indirect prompt-injection content.
Audit Metadata