security-guidance
The security-guidance plugin performs three-layer security review on Claude-generated code: pattern-based warnings for ~25 known-dangerous patterns on edit, LLM-powered diff review on Stop to catch high-severity findings, and agentic commit review that traces data flow across files to catch multi-file vulnerabilities like IDOR, auth bypass, and SSRF. It configures via environment variables to select models, disable layers, or enable higher-recall mode with dual review calls.
Install
Source: https://github.com/anthropics/claude-plugins-official/tree/HEAD/plugins/security-guidance
What it's made of
12 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 12 · PostToolUse, SessionStart, Stop, SubagentStop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
bash- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Featured in
- ♪ TikTok · Check link in bio for in depth guides. Four free Claude Code plugins that change how Claude writes code. Two are official Anthropic plugins, one has over 95,000 stars on GitHub, and all four install i — tylermommsen · 11k views · Sun Sep 20
- ▶ YouTube · Make Claude Code 10x More Powerful (Only Plugins You Need) — Cloud-Codes · 5.8k views · Mon Aug 31
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (anthropics).