deep-research

Warn

Audited by Snyk on Apr 16, 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). SKILL.md's Search Strategy and Extraction steps explicitly require fetching/scraping public third-party sites (e.g., "site:arxiv.org", "site:github.com") and instruct the agent to extract and interpret claims from those sources to drive fact-checking and outputs, which could let untrusted page content influence tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 05:27 PM
Issues
1