search-page-audit

Warn

Audited by Snyk on Mar 2, 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 "Step 1: Fetch & Parse" explicitly requires fetching and parsing the provided URL's full HTML/rendered content and domain files (robots.txt, sitemap.xml, llms.txt), so the agent ingests arbitrary public web content that directly drives audit decisions and could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 10:01 PM