implement

Warn

Audited by Snyk on May 12, 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). The skill's Map Phase and coordination docs (e.g., shared/coordination/map-phase.md and related Map/Reduce guidance) explicitly permit and instruct agents to use WebFetch and browser navigation (mcp__claude-in-chrome__navigate / get_page_text) to fetch and read arbitrary web URLs, meaning untrusted third‑party page content is ingested and can influence agent analysis and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 04:06 AM
Issues
1