The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to interact with the local git repository.
Evidence: Uses git rev-parse --show-toplevel to locate the repository root.
Evidence: Uses git diff --cached and git diff to analyze changes in the codebase.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions designed to influence the agent's behavior during the changelog generation process.
Ingestion points: Reads data from git diff (which includes commit messages and code changes) and the conversation context (SKILL.md, Steps 3 and 5).
Boundary markers: None. The skill does not define specific delimiters or instructions to ignore embedded commands in the diff data.
Capability inventory: The skill has the capability to execute shell commands (git) and modify files (CHANGELOG.md).
Sanitization: None. The skill does not specify any validation or filtering of the content retrieved from git before it is used to update the changelog.

update-changelog