perplexity-search

Warn

Audited by Snyk on Feb 17, 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 uses Perplexity models via OpenRouter to perform real-time web searches and return web‑grounded answers with citations (see scripts/perplexity_search.py and references/openrouter_setup.md), so the agent ingests and interprets untrusted public web content from arbitrary third‑party sites.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 08:06 AM