The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a Python script (scripts/collect_commits.py) to execute local git commands such as git log, git tag, and git describe using the subprocess.run method. These commands are used to fetch repository history and are essential for the skill's stated purpose of generating changelogs.
[PROMPT_INJECTION]: The skill processes external data in the form of git commit messages. This creates a surface for Indirect Prompt Injection, where a malicious actor could include instructions within a commit message (e.g., "Ignore previous instructions and do X") to influence the AI agent's behavior during the changelog generation process.
Ingestion points: Commit history retrieved via git log in scripts/collect_commits.py.
Boundary markers: None present; commit data is fed directly into the agent's context.
Capability inventory: File-writing (to CHANGELOG.md) and shell command execution (via subprocess.run in scripts/collect_commits.py).
Sanitization: None; the raw commit subject and body are printed for the agent to process.

write-changelog