skills/cloudvoyant/codevoyant/mise/Gen Agent Trust Hub

mise

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates and recipes for defining shell tasks in mise.toml. These tasks interact with developer tools such as Docker, Terraform, pnpm, Zig, and Conan to perform builds, tests, and deployments.
  • [EXTERNAL_DOWNLOADS]: The Docker setup recipe in references/recipes/docker.md includes instructions to download and install the mise tool directly from its official domain (https://mise.run).
  • [PROMPT_INJECTION]: The skill uses the $ARGUMENTS variable in SKILL.md to ingest user input from slash commands, which constitutes a potential surface for indirect prompt injection, though it is a standard implementation for parameter handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 02:35 PM
Security Audit — agent-trust-hub — mise