$ loading_
Scan AI agent skills locally to detect security risks before installation.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.YottaMeta/yotta-verify-mcp" MCP server from askskill: Run: claude mcp add 'io-github-yottameta-yotta-verify-mcp' -- npx -y @yottameta/yotta-verify-mcp
Developers can run a quick validation before submitting or publishing an AI agent skill to catch suspicious configuration and security defects. The tool provides offline risk findings and reduces post-install incidents.
For operations teams in air-gapped or strict environments, introducing new skills cannot upload code externally. This MCP runs local static scanning, meeting the no-upload compliance requirement.
Teams can add this scan as a pre-install gate in onboarding workflows, filtering security issues first before deployment or further testing to improve reliability.
It is a pre-install security scanner for AI agent skills. It runs as a local stdio MCP and performs offline static scanning to help detect issues before installation.
The description explicitly states offline static scanning and "no upload," so scan contents are not intended to be uploaded.
The provided information does not include full installation steps, keys, or runtime prerequisites. See the source repository for full setup details.
Statically scan MCP servers, skills, and plugins for security risks.
Score trust and safety before installing MCP servers, AI skills, or npm packages.
Scan AI skill packages for malicious docs and scripts before execution.
Scan AI skills before install for injections, leaks, and supply-chain risks.
Scan AI agents, MCP servers, and skills for security risks.
Scan skills, MCP configs, and agent content for injection and supply-chain risks offline.