The Agent Skills Directory

[SAFE]: The skill operates entirely within the scope of its described functionality, using standard development practices for Git repository management.
[COMMAND_EXECUTION]: The skill suggests the use of standard command-line utilities to perform repository operations.
Evidence: Use of git log, git describe, git tag, gh release create, and sed for processing history and managing releases.
Context: These commands are required for the skill's primary purpose and do not indicate malicious intent.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of Git commit messages, creating a standard injection surface common to documentation tools.
Ingestion points: Commit messages retrieved via git log in the 'Generation Process' and 'Workflow Integration' sections of SKILL.md.
Boundary markers: The output is structured in Markdown sections, but no specific boundary markers are used to isolate commit text from the agent's parsing logic.
Capability inventory: The skill utilizes shell command execution (git/gh) and file system write access (CHANGELOG.md).
Sanitization: The logic uses regex patterns (conventionalRegex) to parse commit structures, which provides structural validation but does not sanitize the content of the commit descriptions themselves.

changelog