The Agent Skills Directory

[SAFE]: The skill is designed to assist with developer workflows by generating commit messages based on staged and unstaged changes. It uses standard Git commands (git status, git diff) which are appropriate for its stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from repository diffs and file contents.
Ingestion points: Data enters the context through git diff and git status command outputs as described in the Process section of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed diffs.
Capability inventory: The skill is limited to git status and git diff tools as defined in the allowed-tools metadata.
Sanitization: No explicit sanitization or filtering of the diff content is performed before generating the commit message.

commit-message