mise-expert
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The documentation includes examples for CI/CD and Docker environments that use
curl https://mise.run | sh. This is the official installation method for the mise CLI. - [EXTERNAL_DOWNLOADS]: The skill is designed to facilitate the download and installation of various language runtimes (Node.js, Python, Go, Ruby, etc.) and developer tools from their respective official registries using the mise manager.
- [COMMAND_EXECUTION]: A core feature of the skill is managing and running shell tasks defined in
mise.toml. Examples include build scripts, database migrations, and deployment commands. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it is designed to process external project configurations.
- Ingestion points: Reads
mise.toml,.tool-versions, and.envfiles from the project workspace. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the data ingested from these configuration files.
- Capability inventory: The skill has the capability to execute shell commands, manage files, and install software packages.
- Sanitization: No specific sanitization or validation of the content within the configuration files is described.
Audit Metadata