Research
Warn
Audited by Snyk on Feb 16, 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 invokes the research CLI to call Perplexity, Gemini, and Claude/WebSearch (e.g., ~/.claude/bin/research --all or --perplexity/--gemini), which returns JSON "content" and "citations" (URLs) drawn from open web sources — meaning the agent ingests and interprets untrusted third‑party web content.
Audit Metadata