cli-anything

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the tool's source code from its official GitHub repository (https://github.com/HKUDS/CLI-Anything.git) and describes functionality for cloning remote repositories from user-provided URLs.
  • [COMMAND_EXECUTION]: The documentation outlines standard development workflows, including package installation using pip install -e . and the execution of test suites via pytest. These actions are intended for setting up and verifying the generated CLI tools.
  • [PROMPT_INJECTION]: The 'Self-Evolving Skill' and 'Post-Execution Reflection' sections include directives for the AI agent to autonomously modify the SKILL.md file based on usage outcomes. While presented as a maintenance feature, this instructs the agent to persist changes to its own operational guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 09:46 AM