blitzreels-video-editing
Warn
Audited by Snyk on May 7, 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 ingests arbitrary public media (e.g., "upload-url" in SKILL.md and editor.sh, and
POST /workspace/media/import/youtubein references/clipping.md) and instructs the agent to read transcripts/context (/projects/{id}/context, /transcript, captions endpoints) and act on that content (apply caption fixes, clipping, automatic-layout), so untrusted third‑party content can materially influence tool use and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata