The Agent Skills Directory

[SAFE]: The skill consists of natural language instructions for a developer agent to perform a specific refactoring task. It focuses on identifying code patterns that indicate inlined functions or macros and restoring the original abstraction level.
[COMMAND_EXECUTION]: The skill mentions using standard tools such as rg (ripgrep) for code searching and a build command to verify code correctness after refactoring. These are routine operations for a coding-focused AI agent.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code (decompiled functions). While this is an attack surface where malicious code could attempt to influence the agent's behavior, the risk is inherent to the skill's primary purpose of code analysis and no specific vulnerabilities are introduced by the instructions.

helper-recovery