The Agent Skills Directory

[SAFE]: The skill is a Markdown file defining coding standards and naming conventions for Ensi projects, following PSR-1, PSR-2, and PSR-12.\n- [SAFE]: No malicious code, remote downloads, or credential exfiltration patterns were detected. All code snippets provided serve as stylistic examples and are benign.\n- [SAFE]: No prompt injection, obfuscation, or persistence mechanisms were found.\n- [SAFE]: Indirect prompt injection surface analysis: The skill processes project-specific source code for review and modification. (1) Ingestion points: PHP source files and Laravel components as defined in SKILL.md. (2) Boundary markers: No explicit delimiters are specified in the instructions. (3) Capability inventory: The skill guides the agent in writing, refactoring, and modifying project source files. (4) Sanitization: No sanitization or input validation is specified. This surface is assessed as safe given the skill's purely instructional and stylistic nature.

ensi-code-style