translate-video
Fail
Audited by Snyk on Nov 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a plausible subtitle pipeline, but Step 6 runs an undocumented local binary (
~/.local/bin/ffmpeg-ass) that is absent from DEPENDENCIES.md and unexplained, which is sketchy but shows no malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow transcribes a user-selected video file (SKILL.md Step 1) and then reads the resulting transcript (.md and .srt) to translate it, so any outsider-authored speech in a video the user chose to process reaches the LLM, but the agent does not monitor a feed and an outsider cannot force delivery.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata