configure

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly configures and enables scanning public, user-generated sources (e.g., Hacker News and GitHub via configure_sources hackernews_enabled/github_enabled), so the agent will ingest untrusted third-party content that can influence its scoring and behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 02:19 AM