deep-research

Warn

Audited by Snyk on May 10, 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's SKILL.md (see "Phase 3 RETRIEVE
  • Mandatory Parallel Search" and the methodology examples) explicitly instructs launching WebSearch/mcp__Exa__exa_search/WebFetch calls against public websites (e.g., arxiv.org, industry/news sites) and then mandates reading, triangulating, and acting on those retrieved sources to drive synthesis, spawning agents, and recommendations, which clearly ingests untrusted third‑party content that can influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 10, 2026, 01:19 PM
Issues
1
Security Audit — snyk — deep-research