NYC

omnisearch

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: 1.00). OmniSearch explicitly runs web searches via ./scripts/omnisearch.sh (and fallback mcporter web_search/ai_search) against public providers (perplexity, brave, kagi, tavily, exa) and instructs the agent to read, summarize, and cite source URLs from the open web, which are untrusted third‑party/user‑generated content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:57 AM