The Agent Skills Directory

[SAFE]: No malicious behavior detected. The skill implements standard DevOps workflows using official utilities (git, gh). All shell commands and logic are transparent and consistent with the described purpose of managing releases.
[PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes external repository data.
Ingestion points: Existing pull request descriptions are retrieved using gh pr view and commit hashes via git log.
Boundary markers: No explicit delimiters or warnings are used when interpolating retrieved data into new pull request bodies.
Capability inventory: The skill has access to the Bash tool to execute git and gh operations.
Sanitization: No explicit sanitization or escaping of the fetched repository content is performed before it is used in subsequent command execution.

release