opusclip

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly ingests public, user-generated video content via create-project --url (SKILL.md / references/api-reference.md list YouTube, Vimeo, X, etc.) and then instructs the agent to read and display human-readable fields (titles, descriptions, hashtags) using get-clips --summary and the preview command (scripts/opusclip and templates/preview.html), so untrusted third-party content is read and can influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 02:51 AM