deep-research

Warn

Audited by Snyk on Mar 4, 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). This skill's required workflow (SKILL.md "Deep Research" Phase 2 and the "When to Use" sections) explicitly instructs the agent to perform web research and use web_fetch to read full content from external/public web sources and follow references, so the agent will ingest untrusted third‑party content that can influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:22 AM