The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands to perform repository operations and project-specific tasks.
It executes git diff, git log, gh pr diff, and gh pr view to gather information about code changes.
It uses mise run changelog:new to generate new changelog fragment files.
It runs go test to validate that the changelog files are correctly formatted and parsable.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from commit messages and pull request descriptions, which could potentially contain malicious instructions.
Ingestion points: Untrusted data enters the agent's context through git log and gh pr view output in the 'Find what the branch changed' section of SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the retrieved git/GitHub data as untrusted or to ignore instructions embedded within that data.
Capability inventory: The skill has access to shell execution via git, gh, go, and mise. The mise command allows for writing new files to the repository.
Sanitization: The skill does not implement sanitization or filtering for the content retrieved from commit bodies or PR descriptions before processing them to generate release notes.

release-notes