citation-validator

Warn

Audited by Snyk on Feb 15, 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). This skill explicitly instructs the agent to use WebSearch/WebFetch to retrieve and read external web sources as part of "Step 5: Citation Accuracy Verification" and the "Tool Usage" sections, meaning it ingests open/public third-party web content (reports, news, websites) that could carry untrusted/user-generated content and enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:33 PM