The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard shell-based git commands including git status, git diff, git add, and git commit. These operations are fundamental to the skill's purpose. The instructions include a 'Git safety protocol' that explicitly forbids destructive actions (like --force or hard reset) and configuration changes, which mitigates the risk of misuse.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it ingests and analyzes git diffs, which can contain untrusted data. A malicious diff could be crafted to include instructions that attempt to influence the generated commit message or manipulate the agent's logic.
Ingestion points: Git diff output obtained via git diff and git diff --staged is used as the primary data source for analysis in SKILL.md.
Boundary markers: The skill does not define specific delimiters or 'ignore' instructions for the diff content provided to the model.
Capability inventory: The skill has the capability to stage files (git add) and execute commits (git commit) through the shell.
Sanitization: There is no evidence of sanitization or filtering of the content extracted from the git diff before it is processed by the agent.

git-commit