blog-factcheck

Warn

Audited by Snyk on Mar 19, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches cited web pages via WebFetch as part of its verification workflow (SKILL.md Step 3: "Fetch the source page via WebFetch") and then reads and interprets that arbitrary third-party page content to assign confidence scores and decide follow-up actions, so untrusted web content could inject instructions that influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 19, 2026, 09:08 AM
Issues
1