The Agent Skills Directory

Instructional Safety (SAFE): The skill instructions in SKILL.md are strictly professional and focus on code quality and structure. No prompt injection or behavior override patterns were detected.\n- Indirect Prompt Injection (SAFE): The skill is designed to process external code (Ingestion: Read, Grep, Glob tools) and has permissions to modify the filesystem and run commands (Capabilities: Write, Edit, Bash). This surface is inherent to its primary purpose and no exploitation patterns were found. (Boundary markers: Absent; Sanitization: Absent).\n- Data Security (SAFE): There are no hardcoded credentials, sensitive file paths, or unauthorized network operations in the provided files.

refactoring-specialist