yt-research
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via
scripts/yt_transcript.sh, which calls TranscriptAPI for a user-supplied YouTube URL/id and returns the video’s caption/transcript text (authored by someone other than the operating user) as readable prose.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata