video-frames
Warn
Audited by Snyk on Jul 23, 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). SKILL.md’s workflow ingests outsider-authored free text from the video frames themselves (on-screen text/OCR/transcription) into the LLM context via the “Read tool” in Step 4 “Vision analysis,” even though it is treated as untrusted data.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata