mise
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from existing repository files during migration procedures, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The 'Procedure: migrate from another manager' in
SKILL.mdinstructs the agent to read legacy configuration files (e.g.,.nvmrc,Brewfile,.tool-versions) and README files.\n - Capability inventory: The skill utilizes shell commands such as
mise install,mise trust, andmise lsas described in the setup and migration procedures inSKILL.md.\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded content within the source migration files.\n
- Sanitization: There are no specific steps defined for sanitizing or validating the contents of the legacy files before they are used to generate the new configuration.\n- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands, including
mise trustandmise install, to configure the environment and install tools. These commands are fundamental to the tool's operation but represent an execution capability that could be misused if the configuration files were tampered with.
Audit Metadata