deep-research
Warn
Audited by Snyk on Feb 15, 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). This skill explicitly instructs the agent to fetch and scrape open/public third‑party sources (e.g., via MCP tools like "mcp__firecrawl__firecrawl_scrape"/"exa", and fallback "WebFetch"/"WebSearch") and to save raw crawled pages under .research//raw/, so the agent will read and interpret untrusted web/social content as part of its workflow.
Audit Metadata