The Agent Skills Directory

[SAFE]: The skill focuses on local code quality management using established OCaml tooling. No malicious patterns such as data exfiltration, credential harvesting, or unauthorized remote code execution were identified.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user-provided OCaml source files (.ml, .mli).
Ingestion points: Local source files within the user's workspace are scanned by the tool.
Boundary markers: The instructions emphasize tool-based execution and status reporting rather than raw prompt interpolation, reducing risk.
Capability inventory: The skill uses ocamlformat for checking and formatting code, which is a standard developer workflow.
Sanitization: The instructions include a mandatory requirement for users to review diff outputs before accepting any automated code modifications.

codeguard-ocaml