web-deepsearch

Warn

Audited by Snyk on May 9, 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.md explicitly requires fetching and ingesting content from external web sources (see "Scope: Research external knowledge from web sources", "Phase 2: Generate the Search Plan" and "Phase 3: Collect and Rank Evidence" with numbered citations and full URLs), which are open/public third‑party sites whose content the agent must read and use to drive decisions and recommendations.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 05:03 AM
Issues
1