youtube-processor
Warn
Audited by Snyk on Sep 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent skill extracts and ingests transcripts from arbitrary YouTube videos via local CLI tools or an external API endpoint, exposing the workflow to outsider-authored free text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill references an external Vercel hosting endpoint (
https://youtube-processor-eight.vercel.app/transcript?url=...) as an alternative operational execution path for fetching transcripts via WebFetch, but its publisher provenance is unknown and arbitrary.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata