sentinel-ai-safety
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscati…
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.
Contains
1 plugin.
Install
/plugin marketplace add MaxwellCalkin/sentinel-ai
Then browse and install with /plugin install.
Source
Repository: https://github.com/MaxwellCalkin/sentinel-ai
Maintain sentinel-ai-safety?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[sentinel-ai-safety on getagentictools](https://getagentictools.com/plugins/maxwellcalkin-sentinel-ai-safety?ref=badge) Related plugins
vibe-ship Marketplace for the vibe-ship plugin: generates and audits production-ready deployment setups (Docker, CI/CD, security, scalabili…
dev-tools Claude Code plugin marketplace: Drupal development, DDEV, Docker, CI/CD, git workflows, and OWASP ASVS security
insightflo A Claude Code skills and project-team toolkit repository for standardized workflows, governance automation, and quality/securi…
claudesec Security scanner, ISMS dashboard, and asset management for AI-assisted development
github-autopilot GitHub Autopilot — AI repo assistant. Analyze PRs, fix issues, scan secrets from your IDE.
soundcheck Simple security reviews for AI agents