Le catalogue réel des outils pour IA

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Scans RAG content/scraped pages for indirect prompt injection

MCP for Roblox Studio and Open Cloud: drive Studio, run headless tests, and review game security.

Audit AI agent configs for prompt injection & rogue MCP servers; vet packages

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

Scan for prompt injection, secrets, PII, and vet MCP servers before installation

Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.

MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026

Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.

Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.

Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.