blog-analyze

Warn

Audited by Snyk on Feb 26, 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.md explicitly states under Input Handling that it supports "URL: Fetch with WebFetch, extract content", so the agent will retrieve and interpret arbitrary published web pages (untrusted third-party content) which directly influence scoring, recommendations, and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 01:28 AM