perplexity-search
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: 0.90). This skill performs web searches and AI-synthesized research via Perplexity (e.g., scripts/mcp/perplexity_search.py with --search/--research/--deep), which fetches and ingests content from open/public websites and sources, so the agent will read untrusted third-party content.
Audit Metadata