anthropic-security-guidance

Name: anthropic-security-guidance
Author: EricGrill

EricGrill ★ 21

anthropic-security-guidance detects vulnerabilities in Claude-generated code through three layers: instant regex pattern warnings on edits, LLM-powered diff review at turn completion, and agentic commit review that traces data flow across files to catch injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes. Configuration via environment variables lets you select the review model, enable/disable individual layers, and define org-specific security policies.

Security Code Review No API key detected runs shell

Install

> /plugin marketplace add EricGrill/agents-skills-plugins/tree/HEAD/plugins/anthropic-security-guidance

> /plugin install anthropic-security-guidance

Source: https://github.com/EricGrill/agents-skills-plugins/tree/HEAD/plugins/anthropic-security-guidance

What it's made of

9 hooks

Commands: 0
Agents: 0
Skills: 0
MCP servers: 0
Hooks: 9 · PostToolUse, SessionStart, Stop, UserPromptSubmit

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: bash
Talks to: nothing external detected

Analyzed 2026-11-01. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (EricGrill).