self-improving
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). Yes — the skill explicitly searches and installs packages from the public PRPM registry (via prpm search / prpm ai-search and prpm install) and then "loads package knowledge" including community/unverified packages, so the agent ingests and interprets untrusted third‑party content.
Audit Metadata