geo-fact-checker

Warn

Audited by Snyk on Mar 10, 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 explicitly instructs the agent to use live web tools ("a web search tool e.g., WebSearch" and "a web fetch tool e.g., WebFetch") in SKILL.md (see "Available tools" and step 4 "Run fact checks using tools") to fetch and read public webpages/URLs and then base verification decisions and next actions on that content, which meets the criteria for ingesting untrusted third‑party material that can influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:57 AM