The Agent Skills Directory

[SAFE]: The skill follows a structured workflow designed to preserve observable behavior while improving code structure. It uses an 'assume-safe' posture with detailed checklists for architecture, performance, and security audits.
[SAFE]: The included security reference guide (references/security.md) provides accurate and beneficial instructions for detecting vulnerabilities such as SQL injection, hardcoded secrets, and unsafe deserialization in target codebases. This enhances the security of the refactoring process rather than compromising it.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the instructions or reference files.
[SAFE]: While the skill involves processing untrusted user code (Indirect Prompt Injection surface), the instructions explicitly mandate behavior preservation, incremental changes, and verification through tests, which are standard and safe practices for development-oriented agents.

refactoring-code