director
Warn
Audited by Snyk on Apr 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: 0.90). The skill explicitly downloads and ingests user-provided reference video URLs during intake ("If user provides reference video URLs — download first: bash ${CLAUDE_PLUGIN_ROOT}/skills/video-download/scripts/download-video.sh ''") and then analyzes and uses those external materials (material-ingest, Gemini analysis, material-pool.json, and ref_video chaining) as inputs that influence prompt generation and downstream tool actions, so arbitrary third‑party content can indirectly inject instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata