pint-compute

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected.
  • [COMMAND_EXECUTION]: The skill executes a local Python script to perform calculations. This is consistent with its stated purpose of providing unit-aware computation.
  • [PROMPT_INJECTION]: The skill processes untrusted input strings for unit conversion and calculations. 1. Ingestion points: User-provided strings in parse, convert, calc, check, and simplify commands. 2. Boundary markers: None present. 3. Capability inventory: Executes commands via Bash tool using uv run python. 4. Sanitization: Not mentioned in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:04 AM
Security Audit — agent-trust-hub — pint-compute