shapely-compute

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script at 'scripts/shapely_compute.py' using the 'uv' package manager to perform geometric calculations. It passes geometry definitions as command-line arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data via geometry parameters. Ingestion points: '--coords', '--geom', '--g1', and '--g2' arguments in SKILL.md. Boundary markers: Absent. Capability inventory: Local script execution via 'uv run'. Sanitization: No explicit input validation or sanitization is mentioned in the skill instructions.
  • [SAFE]: No obfuscation, data exfiltration, or attempts to bypass safety filters were found. The skill's operations are consistent with its stated purpose of geometric computation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:04 AM
Security Audit — agent-trust-hub — shapely-compute