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: 0.80). The skill automatically searches and installs packages from the public PRPM registry (via the prpm search/prpm install workflow) and then loads/applies package knowledge, meaning it ingests and interprets arbitrary third‑party package metadata/code (including community/unverified packages) that could contain malicious or instructional content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:53 AM