jurisprudence

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.md explicitly directs the agent to run MCP searches (juri_rechercher_cassation / juri_rechercher_complet) and to "Lis le contenu complet" of selected decisions via juri_get_decision (with provision for Légifrance URLs), so it fetches and interprets external public judicial webpages whose content directly drives the agent's synthesis and recommendations.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 7, 2026, 07:27 PM
Issues
1