The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected.
[COMMAND_EXECUTION]: The skill uses the Bash tool restricted specifically to running npx jest for unit testing. This is a common and safe practice for verifying code changes in a development environment.
[DATA_EXPOSURE]: The skill uses file-reading tools like Read, Grep, and Glob to analyze the local codebase as requested in the $ARGUMENTS, but it contains no instructions or network tools to exfiltrate this data.
[INDIRECT_PROMPT_INJECTION]: The skill processes local source code which could theoretically contain malicious instructions in comments. However, the use of sub-agents with specific descriptions and the requirement to pass tests before and after refactoring significantly mitigates the risk of unauthorized behavior modification.

simplify