mvu-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run build commands and grep for symbols to verify the state of the codebase during refactoring. These actions are consistent with the skill's primary function and intended use case.
- [PROMPT_INJECTION]: The skill processes external implementation plans and project source files, representing a surface for indirect prompt injection. This is evaluated as safe as it is central to the skill's function.
- Ingestion points: External implementation plans, CMakeLists.txt, and application source files as described in SKILL.md.
- Boundary markers: Absent; the agent is instructed to read and implement the content of the attached plan directly.
- Capability inventory: Includes grep utilities, file modification, and project build system execution.
- Sanitization: The instructions do not include validation or sanitization steps for the content of the external plan or project files.
- [EXTERNAL_DOWNLOADS]: The skill references an external repository for the elomaxz library (github.com/elomaxz/elomaxz) to guide implementation. No automated remote code execution or script downloading is defined in the instructions.
Audit Metadata