PluginOfficialAnthropic
Security Guidance
Catches vulnerabilities in code written by Claude: injection, XSS, SSRF and secrets.
Anthropic’s plugin works on three levels: on edit it warns about roughly 25 dangerous patterns, after each turn it reviews the diff with a model and sends serious problems back to be fixed, and on git commit an agent traces data flow across files, catching issues such as IDOR and authorization bypass. It requires Python 3.8+.
Installation
Manual install
/plugin install security-guidance@claude-plugins-officialDetails
- Works in
- Claude Code
- License
- Apache-2.0
- Tasks
- Code
- Rating
- Source
- github.com/anthropics/claude-plugins-official/tree/main/plugins/security-guidance (opens in a new tab)
Tags
- security
- xss
- ssrf
- secrets
- review
A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.