short-video-scripter
Warn
Audited by Snyk on Aug 20, 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). In SKILL.md, the runtime “Procedure” explicitly has the agent reads and ingests user-provided free text (“video idea, draft script, or transcript”) and then uses it to generate hooks and beat-sheet script lines, so outsider-authored text can flow directly into the LLM without requiring selection of a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata