deep-research

Warn

Audited by Snyk on Feb 28, 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). Yes — SKILL.md explicitly instructs the agent to perform web searches and ingest open/public sources (e.g., "Execute searches in parallel" and the required "Sources (URLs or doc sections)" with examples like redis.io and medium.com), meaning untrusted third‑party content can be read and materially influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 02:06 PM