auto-skill-guide

Warn

Audited by Snyk on Feb 16, 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 can discover and install community skills from external repos (e.g., "npx skills find" / "npx skills add owner/repo") and dynamically retrieves and loads skill content from a registry ("Scripts retrieve and format skill content on demand" / "SKILL LOADED... "), so the agent will read and execute untrusted third-party skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:07 AM