chengfeng-visual
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Source
SKILL.mdspecifies that the runtime reads user-providedsubtitles.json/transcript.jsonto create cue-by-cue tasks (“① 文字定任务 读 subtitles.json…”), meaning outsider-authored free text can be ingested into the workflow without pre-selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata