The Agent Skills Directory

[SAFE]: The skill performs routine software release tasks that are consistent with its stated purpose and the provided author context.
[COMMAND_EXECUTION]: The skill executes local shell commands and scripts to manage the release cycle.
Evidence: Uses git for branching and tagging, gh for PR management, and local scripts like ./scripts/bump-version.sh and ./scripts/release-pretag-guard.sh for metadata updates.
Context: These operations are restricted to standard development workflows within the project repository and involve expected release management tools.
[PROMPT_INJECTION]: The skill processes metadata from external sources such as Git logs and GitHub PRs/issues, which represents a potential indirect prompt injection surface.
Ingestion points: Reads contributor handles and change descriptions from git log, gh pr view, and gh issue view in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the retrieved data.
Capability inventory: The agent has the ability to modify the repository (git commit/push/tag) and execute local scripts.
Sanitization: No explicit sanitization or validation of the data retrieved from external GitHub sources is described.

release