🛡️ Agent-native AI tool security scanner. Scan MCP/Skill/GPT/Prompt for security risks. 4-dimensional scoring. Certified badges. Guardrail MCP for auto-protection.
This repository also configures its own agents. See what aishield tells them →
Skill Claude CodeCodex
A Chinese-language website review guide covering search-engine visibility, legal checks in mainland China, and AI-agent visibility. It includes checks for items such as robots.txt, sitemaps, ICP registration, llms.txt, agent cards, and structured data.
Skill Claude CodeCodex needs its repo
A security scanner for MCP servers, agent configurations, and AI skills. It checks for risks such as tool poisoning, memory poisoning, excessive permissions, and sandbox escape, and can produce SBOM and SARIF reports.
Skill Claude CodeCodex
Local, open-source security scanner for MCP servers, AI agent skills, GPTs and prompts. Produces a 4-dimensional (security / privacy / quality / performance) score plus an optional certified badge. Scans static artifacts only — it never executes commands from the config being scanned, and your code never leaves your…
Skill Claude CodeCodex
An AI and MCP security scanner aligned with the OWASP MCP Top 10, a list of common risks for tool-connected AI systems. It checks for issues such as prompt injection, command injection, poisoned tools, leaked secrets, unsafe permissions, supply-chain attacks, SSRF, and banned Chinese-language content.
Skill Claude CodeCodex
Scan MCP servers, AI skills, GPTs and prompt files for security risks before installing or shipping them — tool poisoning, prompt injection, over-broad permissions, supply-chain and agentic-ASI01–10 risks. Local-first and zero-dependency: runs fully offline and never executes the scanned code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: