No security issues detected in anthropics/claude-code/writing-rules.
Claims to do
Writing Hookify Rules: Hookify rules are markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. Rules are stored in `.claude/hookify.{rule-name}.local.md` files.
Actually does
This skill provides comprehensive instructions and syntax for creating and managing 'Hookify Rules.' These rules are markdown files stored locally in `.claude/hookify.{rule-name}.local.md` that define Python regex patterns to match against various agent events (bash commands, file operations, agent stop intentions, user prompts). When a pattern matches, a specified message is displayed to the agent, and an action (warn or block) can be triggered. The skill also suggests using `python3` for testing regex patterns and references online regex testers.
[](https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/writing-rules)<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/writing-rules"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/writing-rules.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/writing-rules.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.