The Agent Skills Directory

[SAFE]: The skill provides documentation and reference material for creating and managing Hookify rules. No security vulnerabilities were detected in the instructions or examples.
[PROMPT_INJECTION]: The skill documents the /egc-hookify command which ingests user descriptions to generate rule files. This creates a surface for indirect prompt injection. Ingestion points: User-provided rule descriptions via the command arguments. Boundary markers: None specified. Capability inventory: Writing rule configuration files to the .gemini/ directory. Sanitization: Not explicitly addressed in the documentation.

hookify-rules