Safety scanning
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript SDKs. MCP proxy. Claude Code hooks.From the repository description
npx -y skills add MaxwellCalkin/sentinel-ai --skill safety-scanningAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.