AGENT LAB: SKILLS

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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:52 PM