math-model-selector
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a decision tree for mathematical framework selection. It does not include any executable scripts, shell commands, or network-based operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input in the form of problem descriptions to recommend mathematical frameworks.
- Ingestion points: User descriptions of mathematical problems are processed through a series of qualitative questions (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands in user input.
- Capability inventory: None; the skill provides descriptive output and does not have access to file system writes, network requests, or subprocess execution.
- Sanitization: Absent; user input is processed as natural language without filtering.
Audit Metadata