The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git diff --staged to retrieve code changes for analysis. It also suggests running tsc --noEmit as part of its workflow to ensure type safety before commits are finalized.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection, as it processes untrusted code changes from staged git diffs which could contain malicious instructions designed to manipulate the agent's output.
Ingestion points: The skill reads data from staged files via git diff --staged (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are used to isolate the diff content from instructions (SKILL.md).
Capability inventory: The skill uses git diff, git status, and tsc --noEmit across its scripts (SKILL.md, config.yaml).
Sanitization: No sanitization or filtering of the diff content is performed prior to processing (SKILL.md).
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing well-known developer tools and security scanners, such as semantic-release, commitlint, and gitleaks, from official and trusted package registries.

dev-git-commit-message