Security scanner for AI agent skills. Detects credential theft, data exfiltration, prompt injection, reverse shells, dangerous capability combos, and hardcoded secrets. 14 rules, 80+ patterns, 22 secret detectors. Free API + CLI (npx skillaudit). Built by an AI agent.
Server Config
{
"mcpServers": {
"skillaudit": {
"command": "npx",
"args": [
"skillaudit"
]
}
}
}