The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and templates. It does not include any scripts (Python, Node.js, Shell) or binaries, nor does it attempt to perform any network or file system operations.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided data (git logs). While this is an ingestion point for untrusted content, the skill has no dangerous capabilities (e.g., subprocess execution, network requests, or sensitive file access). The impact of any potential injection is confined to the quality and content of the generated text response.

changelog-generator