solo-validate
Warn
Audited by Snyk on Mar 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: 1.00). The skill explicitly instructs the agent to run web searches and ingest external webpages (see SKILL.md steps 2 and 6b which call MCP
web_search/ "WebSearch" and fallback to Grep/Glob/WebSearch) and requires using source URLs/evidence to influence STREAM analysis, Devil's Advocate findings, and PRD decisions, so it will read untrusted third‑party content that can change its actions.
Audit Metadata