investigate-failing-tests

Warn

Audited by Snyk on Feb 20, 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). The skill's workflow (Target Resolution Rule + step 6) requires resolving an explicit user URL or target and delegating to "analyze-website" and loading references/website-analysis//website-analysis.*, which means the agent will ingest and act on open/public website content (potentially untrusted user-provided pages) that can influence its diagnosis and routing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:34 AM