citation-validator

Warn

Audited by Snyk on Mar 18, 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 required workflow (Validation Process Step 5 and the Tool Usage sections in SKILL.md/instructions.md) explicitly instructs the agent to use WebSearch/WebFetch to access and read public third‑party web sources to verify citations, meaning untrusted user-generated or public content will be ingested and can influence verification decisions and actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 02:53 AM
Issues
1