perplexity-search

Warn

Audited by Snyk on Mar 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). The SKILL.md explicitly instructs using Perplexity models via OpenRouter (e.g., scripts/perplexity_search.py and the "Real-time web search" overview) to fetch and interpret live web content and source citations from open/public sites (openrouter.ai/Perplexity and arbitrary web sources), meaning untrusted third‑party content is ingested and used to drive the agent's answers and actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 04:33 AM
Issues
1