The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands like git diff and grep to identify the scope of code changes and to search for existing utility patterns in the repository. These operations are local to the development environment and are appropriate for the skill's stated purpose of code refactoring.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted code and diff data from the repository which may contain malicious instructions targeting the agent.
Ingestion points: Data is brought into the agent's context through the output of git diff and file reads performed via grep or standard file system access.
Boundary markers: The instructions lack specific delimiters or warnings to the agent to disregard potential instructions embedded within the source code being analyzed.
Capability inventory: The skill possesses the ability to read from the repository and write/edit files once the user provides confirmation.
Sanitization: There is no evidence of content sanitization or validation of the diff data before it is interpreted by the agent.

simplify