video-editing
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md’s required editing workflow reads user-provided SRT (“source of truth is timed speech (SRT)”), and that SRT’s cue body text is parsed and then concatenated into LLM-visible plain text via scripts/build_filter.py (parse_srt + cut_cues) and scripts/cut_srt.py (writes out_txt), so outsider-authored caption/transcript text can reach the agent context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata