tomiBraunn/backlight-skill

AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

Zero trace. Full answer. — Transparent Claude API proxy that anonymizes PII and sensitive data before it leaves your environment. From pentesters, to pentesters.

LLM Prompt Injection Detector

Local-first tool that strips emails, secrets, paths, and other identifying content out of your prompts before they reach a cloud LLM — and rehydrates the response locally.

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests over model judgement, because LLM judges agree with human slop labels at chance.

Set of tools to assess and improve LLM security.

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

OpenAI Guardrails - TypeScript / JavaScript