The Agent Skills Directory

[SAFE]: No security issues were detected. The skill contains text-based instructions for an agent to follow when using git tools to group and describe code changes.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of git diffs to plan commit history. This represents a potential attack surface for indirect prompt injection, though the skill's logic is focused on metadata organization (naming and grouping) rather than execution of the diff content.
Ingestion points: Processes diff output from the working tree to determine commit structure.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands in diffs are provided.
Capability inventory: Accesses repository history and state via git and git-hunk tools as specified in the frontmatter.
Sanitization: No explicit sanitization or filtering of the processed diff data is described in the instructions.

logical-commits