AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
AgentShield is a security scanner for AI agent configurations, MCP servers, and tool permissions. It audits Claude Code setups for issues such as exposed secrets, unsafe permissions, hook injection, MCP risks, and prompt injection vectors, and can run through its CLI, GitHub integrations, or an ECC plugin. The catalogue entries extend agent workflows for using AgentShield.
Latest release v1.4.0 — AgentShield v1.4.0 — AI Agent Security Scanner · 22 Mar 2026
These files are affaan-m/agentshield's own configuration. They tell Codex and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
CLAUDE.md A 942 tok .agents/skills/agentshield/SKILL.md A —