security-guidance
PackSecuritySecurity-guidance is a plugin that adds a reminder hook to an AI agent's editing workflow. While the agent edits files, the hook warns it about potential security issues such as command injection, XSS, and unsafe code patterns. This gives the security guidance plugin a role in catching risky code as it is written rather than after the fact.
Unavailable. Delivery for this kind is on the roadmap — not serving yet.
Have an agent setup that supports plugins and hook-based reminders.
What your AI can do with it
- Warns the agent about potential security issues while it edits files
- Flags possible command injection risks in edited code
- Flags possible cross-site scripting (XSS) risks
- Points out unsafe code patterns during editing
Getting started
- Have an agent setup that supports plugins and hook-based reminders.
- Add the security-guidance plugin to that setup.
- Enable the plugin so its reminder hook runs during file editing.
- Edit files with the agent and review the security warnings it raises.
Signals
- GitHub stars
- 148k
- Forks
- 25k
- Last commit
- Sep 2026
Questions
- What kinds of issues does it warn about?
- It warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns.
- When do the warnings appear?
- The reminder hook fires while files are being edited, so warnings surface during the editing process.
- Does it fix the issues automatically?
- The item is described as providing warnings and reminders; it does not state that fixes are applied automatically.
Advanced
- Item type
- plugin
- Key
anthropics-claude-code-security-guidance- Source
- github.com/anthropics/claude-code