The Agent Skills Directory

[SAFE]: No security issues detected. The skill provides instructional content for auditing the alignment between code and documentation.
[PROMPT_INJECTION]: The skill involves processing external documentation and code files (Ingestion points: docs/, internal/). It does not define explicit boundary markers or sanitization procedures for these files. However, the agent's capabilities (Capability inventory: code refactoring, running go test) are used within the scope of a standard development workflow, making this a low-risk ingestion surface inherent to its function.
[COMMAND_EXECUTION]: The instructions reference the use of standard development utilities such as grep, gofmt, and go test for verification. These are expected tools in a coding environment and are used here to maintain system integrity.

surface-contract