The Agent Skills Directory

[SAFE]: No security findings detected. The skill is entirely instructional and operates locally on git diffs to perform code cleanup without automated commits or network activity.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from git branches. [1] Ingestion points: The skill reads git diffs from the current branch. [2] Boundary markers: No delimiters are used to wrap the untrusted code content. [3] Capability inventory: The agent is permitted to edit files on the local filesystem. [4] Sanitization: No sanitization of the code being processed is mentioned.

unslop