create-formal-verification-skill

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill is designed to generate and execute project-local scripts for formal verification. This is the core functionality and is accompanied by instructions for validation and human oversight.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests codebase content to define verification properties, which presents a surface for malicious code comments to influence the logic. 1. Ingestion points: Codebase files and functions as described in the 'Choose the target' section. 2. Boundary markers: Not explicitly defined in instructions. 3. Capability inventory: Ability to run shell commands for verification tools and invoke the '/statechart' skill. 4. Sanitization: Relying on manual human review of the generated skill and its findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 05:09 PM