NYC

mise-tool-management

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 explicitly allows installing and sourcing tools from public third‑party locations (e.g., "my-tool = 'git:https://github.com/org/tool.git'", "npm:typescript", "cargo:...") and includes commands that query remote registries ("mise ls-remote", "mise latest"), which means the agent can fetch and process untrusted, user‑generated content from the open web.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:57 AM