The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git log and grep commands to analyze the local repository. These are standard, read-only operations intended for extracting commit metadata and source code comments to synchronize project documentation.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from the codebase and version history.
Ingestion points: Reads git commit messages via git log and extracts TODO, FIXME, and XXX tags from Java source files using grep.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided execution steps.
Capability inventory: The agent has read access to the filesystem and write access to update markdown files in the docs/ directory.
Sanitization: No explicit sanitization or validation of the strings retrieved from git logs or comments is described before they are incorporated into the project status reports.

update-status