math-help
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill serves as a guide for mathematical tools and does not contain malicious instructions or code.
- [COMMAND_EXECUTION]: Demonstrates the execution of local scripts using the uv tool to perform tasks like equation solving, theorem proving, and data visualization.
- [SAFE]: The skill exposes a surface for indirect prompt injection by processing user-provided math expressions, but this is handled locally by trusted math libraries with minimal risk. Ingestion points are CLI arguments, boundary markers are quotes, capabilities are local execution, and sanitization is performed by the math engines.
Audit Metadata