The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were identified. The skill operates within the scope of local git repository management and text generation.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (git diffs) as its primary input. While it lacks explicit delimiters or instructions to ignore embedded prompts within the diff, the risk is categorized as safe because the generated output (PR text, commit messages) is intended for user review rather than automated execution in a sensitive context.

change-pack