skills/mimukit/skills/skillkit/Gen Agent Trust Hub

skillkit

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform repository maintenance and management tasks. This includes running git commands such as git worktree list and origin/HEAD to determine file serials, as well as project-specific commands like make cheatsheet or repository linters. These actions are within the scope of its primary purpose as a developer scaffolding tool.
  • [EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch tools to facilitate naming collision checks and to retrieve structural ideas from existing skill examples. It references skills.sh as a service for skill discovery and listing, which is consistent with its role in the skill collection ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted user "intent" to generate new agent instructions (SKILL.md files). This risk is addressed through a mandatory review loop where the agent must show the draft to the user for explicit approval and a quality bar that requires objective completion criteria for every step.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 06:37 PM