exa-search

Warn

Audited by Snyk on Jun 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The skill is an Exa API–based semantic search tool, and at runtime it will fetch and ingest public web page text (outsider-authored content) returned by Exa into the agent’s LLM context for summarization/answering.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 03:28 PM
Issues
1
Security Audit — snyk — exa-search