geo-audit

Warn

Audited by Snyk on Feb 27, 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). This SKILL.md explicitly requires using web fetching and search tools to fetch homepage and key pages, robots.txt, brand search results and third-party sources (e.g., Wikipedia, review sites, social media) as part of the mandatory audit workflow, so the agent will ingest and act on untrusted public web content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 07:39 AM