The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for an AI agent. It does not include any scripts, configuration files, or executable commands that could impact the host system.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data in the form of git commit messages and history. While this constitutes an ingestion surface for potential indirect prompt injection, the skill includes explicit security guardrails such as changelog sanitization and strict categorization rules for security-related commits to mitigate these risks.
[DATA_EXPOSURE]: The instructions proactively advise the agent to scrub sensitive information like API keys and internal IP addresses from generated documentation, demonstrating a security-first approach to data handling.

release-management