miniplex
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: 0.70). The skill explicitly instructs the agent to fetch documentation from public raw.githubusercontent.com URLs (the Miniplex README links), which are open third-party sources the agent would read and could contain untrusted or user-provided content.
Audit Metadata