legal-risk-assessment-zacharie-laik

Warn

Audited by Snyk on Mar 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 requires running a web_search (AI-powered web search via Perplexity) for doctrinal commentary and to use returned URIs from web_search results as inline citations (see "Step 2: Doctrinal and web search" in SKILL.md and the citation rules in references/citations.md), which means the agent will fetch and read untrusted public web content that can materially influence its legal analysis and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 08:10 PM