The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or data exfiltration patterns were identified. The skill follows a logical multi-phase approach to code refactoring using coordinated sub-skills.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it processes untrusted code provided by users as its primary input.
Ingestion points: Monolithic source code files are read and processed in Phase 1 (Dependency Analysis).
Boundary markers: The instructions lack explicit delimiters or instructions to the agent to ignore commands potentially embedded in source code comments or strings.
Capability inventory: The skill coordinates filesystem modifications (creating directories and moving code) via the cross-file-refactor capability.
Sanitization: No content validation or escaping is specified for the code content being refactored, allowing potentially malicious instructions in source files to influence the refactoring plan.

code-modularizer