essay-fact-checker

Warn

Audited by Snyk on Feb 21, 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's SKILL.md explicitly requires performing WebSearch and WebFetch ("Tier 1: Process" steps 2 and 4, and Tier 2 uses WebSearch) to retrieve and interpret public web content and use those findings to decide verification statuses, so it ingests untrusted third-party web pages that can materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 09:24 AM