mise
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill describes the functionality of Mise, a legitimate development utility. All external links point to official documentation (https://mise.jdx.dev).
- [SAFE]: The documentation highlights security best practices, including the use of 'mise trust' to prevent execution of untrusted configuration files and recommending '.env.local' for secrets.
- [COMMAND_EXECUTION]: The skill provides examples of using Mise as a task runner. This functionality is the primary purpose of the tool and is accompanied by information on security boundaries to mitigate risks from external scripts.
- [INDIRECT_PROMPT_INJECTION]: As a tool that processes configuration files (mise.toml), Mise has an inherent ingestion surface.
- Ingestion points: mise.toml, .tool-versions, .env.
- Boundary markers: mise trust.
- Capability inventory: Shell command execution (run), Tool installation (backends).
- Sanitization: Manual user review via the trust mechanism.
Audit Metadata