guardskills

Warn

Audited by Snyk on Mar 8, 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.md explicitly instructs the tool to scan and ingest skills from public third‑party sources (e.g., "guardskills scan-clawhub <owner/skill-slug>" and "guardskills add https://github.com/owner/repo"), meaning it fetches and interprets user-generated content from ClawHub/GitHub as part of its decision workflow, so untrusted content could influence installation decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 09:48 AM