critical-reasoning
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown files providing instructions and educational reference material. No executable scripts (Python, Node.js, Shell) or binaries are included in the skill package.
- [EXTERNAL_DOWNLOADS]: The README includes an installation command using
npx. This command targets the official repository of the skill author, which is a standard distribution method for this platform. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze user-provided arguments, creating a surface for potential indirect prompt injection.
- Ingestion points: User arguments are ingested through the prompt interface defined in
SKILL.md. - Boundary markers: The skill uses a structured reasoning process (Steel-man, Test, Evaluate) to handle user input, though no formal data delimiters are specified.
- Capability inventory: The skill does not define any
allowed-toolsand does not call any external functions or system commands. - Sanitization: No explicit sanitization is performed as the skill's output is limited to text-based critique and analysis.
Audit Metadata