create-formal-verification-skill
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted repository content to define verification properties and generate new agent instructions, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads files and functions across the entire repository to identify targets for formal verification.
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts within the codebase being analyzed.
- Capability inventory: The skill is authorized to create new project-local skill files and execute various formal verification tools (e.g., TLA+, SMT verifiers) via the shell.
- Sanitization: The instructions do not specify sanitization or escaping of code-derived strings before they are interpolated into the generated verification skills or commands.
- [DYNAMIC_EXECUTION]: The skill is designed to perform dynamic generation of executable instructions (new agent skills) and shell commands for verification tools based on runtime analysis of the project's codebase.
Audit Metadata