ra-video-wash-pipeline
Warn
Audited by Snyk on Jul 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). Yes—SKILL.md mandates extracting a transcript from a user-supplied video URL/local file via
ra-逐字稿提取skill(and a runtime scripttranscript.py "<url>" --internal), which ingests outsider-authored transcript text from an external/public video source into the agent/LLM context for rewriting (“complete transcript text available to the agent for rewriting”).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata