The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard development scripts including npm run lint, npm run build, and npm run type-check (or npx tsc). These are routine operations within a development environment and align with the skill's stated purpose of verifying code quality before committing.
[DATA_EXPOSURE]: While the skill stages all changes with git add -A, it explicitly directs the agent to identify and exclude sensitive files such as .env and credentials, adhering to security best practices for version control management.
[PROMPT_INJECTION]: The skill processes untrusted data from git log and git diff to generate commit messages. This represents an indirect prompt injection surface.
Ingestion points: SKILL.md Step 1 calls git log and git diff to analyze repository context.
Boundary markers: No explicit markers are provided for the ingested git data.
Capability inventory: The skill has the capability to execute shell commands (git, npm) as specified in SKILL.md.
Sanitization: No sanitization is performed on the data ingested from the git repository before it is used to influence the commit message creation.

checkpoint