kagi-search

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly performs web searches via the Kagi Search API and outputs titles, URLs, and snippets from public websites (see SKILL.md "Web search using the Kagi Search API" and the "Output Format"), which exposes the agent to untrusted third-party content that could contain instructions influencing its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:16 AM