narrative-conductor

Warn

Audited by Snyk on Feb 17, 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's "Recherche et inspiration" section explicitly instructs the agent to "utilise l'outil Browser" to visit web articles, blogs, news sites and YouTube (open/public third‑party sources) and to read/consult that content to enrich the episode, which exposes the agent to untrusted user-generated third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:33 AM