skills/aaronflorey/agent-skills/mise/Gen Agent Trust Hub

mise

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides extensive documentation for the 'mise' utility, covering configuration, task execution, and environment management.
  • [EXTERNAL_DOWNLOADS]: Mentions installing development tools from well-known and trusted sources including GitHub, npm, PyPI (via pipx), and Hashicorp (via aqua). These are documented as core features of the tool's backend system.
  • [COMMAND_EXECUTION]: Describes how to define and run tasks using various interpreters (bash, python, node). The skill highlights the 'mise trust' mechanism, which is a built-in security control to prevent the automatic execution of untrusted configuration files.
  • [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found in the instructions or metadata.
  • [DATA_EXFILTRATION]: No suspicious network operations or unauthorized access to sensitive file paths (like SSH keys or AWS credentials) were detected. The skill correctly documents how to redact sensitive environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 09:45 PM