learn

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). Yes — SKILL.md's "Step 2: Research Best Practices (When Appropriate)" explicitly requires searching the web, reviewing top results, and adding source URLs to a "References" section, which means the agent will fetch/read public third‑party pages and incorporate their content into skills (potentially influencing decisions and tool use).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:53 AM