NYC

ai-multimodal

Warn

Audited by Snyk on Feb 16, 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 accepts and analyzes public YouTube URLs as inputs (see "process videos ... YouTube URLs" and "local/inline/YouTube inputs" in the Video/Video Analysis sections), which are user-generated, untrusted third‑party content that the agent reads and interprets for analysis/Q&A.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:57 AM