Writing Hookify Rules
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (INFO): The skill defines a mechanism for the agent to monitor and act upon external data (files and prompts). While this capability could theoretically be targeted by malicious content in a processed file, it is a first-party governance feature designed to enhance security.
- Ingestion points: Rules process user prompts and file edits via 'prompt' and 'file' events.
- Boundary markers: Policy files are isolated within the .claude/ local directory.
- Capability inventory: Provides the ability to warn the user or block agent actions (PreToolUse).
- Sanitization: Uses regex pattern matching to identify and flag content.
Audit Metadata