maoxuan-skill-cognitive-framework
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions that involve cloning a repository from GitHub (
github.com/leezythu/maoxuan-skill.git) or using a package manager (npx skills add leezythu/maoxuan-skill). This is a standard method for distributing and installing agent skills. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided problems to offer strategic analysis.
- Ingestion points: User input provided via various triggers (e.g., "analyze with mao's mental models").
- Boundary markers: None identified in the instructional text.
- Capability inventory: The skill documentation does not list any dangerous capabilities such as file writing, network operations, or command execution.
- Sanitization: No explicit sanitization or filtering of user input is mentioned, but the lack of high-risk capabilities mitigates the potential for abuse.
Audit Metadata