critic

Warn

Audited by Snyk on Apr 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md defines a POST /v1/watch endpoint that accepts a mediaUrl ([MEDIA_URL]) and requires the agent to analyze external videos/images (quality check, verification, deep analysis) and act on those results (pass/fail, regenerate, change prompts/models), so arbitrary public media supplied via the mediaUrl can provide untrusted content that materially influences behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 01:53 AM
Issues
1
Security Audit — snyk — critic