The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diffs to automatically generate commit messages, which could be exploited to influence agent behavior.
Ingestion points: The skill reads file diffs using git diff commands in Sections 1 and 2.
Boundary markers: The instructions do not define specific delimiters to wrap or isolate the diff content from the agent's instructions.
Capability inventory: The skill possesses significant capabilities, including the ability to stage files, commit them, and push code to remote repositories using the Bash tool.
Sanitization: There is no evidence of sanitization or filtering of the diff content before it is used to generate the commit messages.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute a variety of Git and GitHub CLI commands, including potentially sensitive operations like git push to remote origins.

commitkit