research

Warn

Audited by Snyk on May 8, 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 workflow (e.g., Phase 2 "Wave 1 Template" and Quick Research Mode) explicitly requires using WebSearch/WebFetch and citing URLs—instructing agents to fetch and read public web pages, blog posts, GitHub READMEs and other user-generated sources—which the agent must interpret and synthesize into recommendations, thereby exposing it to untrusted third‑party content that could carry indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 04:18 PM
Issues
1