#118 · Primary category： Cybersecurity & Decryption Tools
agentshield
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. 🛡️
Project last updated：07/22/26
GitHub Stars
1.1K
Forks
231
Contributors
4
License
MIT
Why we included this project
Developer teams pulling community skills, MCP servers, and custom hooks into Claude Code move faster than anyone can vet them, and that ecosystem has already shown how hostile it can get: in January 2026, 12% of the skills on one major marketplace turned out to be malicious. AgentShield automates the audit by scanning your agent configuration directory for hardcoded secrets, overly permissive tool grants, hook injection, risky MCP server connections, and prompt injection vectors. It ships as a CLI, a GitHub Action, or a GitHub App, so you can run a one-off check on your own machine or fold the scan into CI and catch suspicious configs before they reach production. For anyone wiring third-party skills and MCP endpoints into an agent's toolchain, it's a cheap, scriptable sanity check worth running before anything sensitive gets attached.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
reverse-skill
AI-powered skill router for reverse engineering, authorized penetration testing, and security research, with on-demand toolchain bootstrapping and self-evolving knowledge base.
gitleaks
Find secrets with Gitleaks 🔑
osquery
SQL powered operating system instrumentation, monitoring, and analytics.
NeoPass
Your Essential Exam Companion for the Iamneo Portal & NPTEL Exams Disguised as NeoExamShield bypass
anubis
Weighs the soul of incoming HTTP requests to stop AI crawlers