cli-hub-meta-skill
Warn
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the 'cli-anything-hub' Python package and other tool-specific packages from a public registry.
- [REMOTE_CODE_EXECUTION]: The skill facilitates a model where a manager tool installs and executes additional Python packages at runtime. While these packages are associated with the vendor, the dynamic nature of the installation process constitutes remote code execution.
- [COMMAND_EXECUTION]: The instructions involve executing shell commands to install and interact with software tools via 'pip' and the 'cli-hub' interface.
- [PROMPT_INJECTION]: The skill fetches an external 'Live Catalog' from a cloud storage bucket to identify available tools.
- Ingestion points: https://reeceyang.sgp1.cdn.digitaloceanspaces.com/SKILL.md.
- Boundary markers: No explicit markers or warnings are provided to ignore potential instructions within the fetched catalog.
- Capability inventory: The agent has the ability to install and execute system-level packages.
- Sanitization: There is no documented validation or sanitization of the content retrieved from the external catalog.
Audit Metadata