The Agent Skills Directory

[SAFE]: The skill provides benign instructions focused on improving code quality and readability. It does not contain any commands for network access, file system modification (beyond the agent's standard code-editing scope), or credential harvesting.
[EXTERNAL_DOWNLOADS]: The skill references a documentation link from Anthropic's official GitHub repository. This is used for attribution and does not involve downloading or executing remote code.
[PROMPT_INJECTION]: As the skill is designed to process and refactor code from the user's session, it possesses an inherent surface for indirect prompt injection. However, the instructions are well-defined for structural refactoring, and there are no signs of behavior override patterns or bypass attempts.

code-simplifier