The real catalog of tools for AI agents

HMAC-signed zero-width invisible canary token generator and output response leak auditor

Catches leaked credentials and PII in outbound LLM prompts

Catches leaked credentials and PII in outbound LLM prompts

Check text before your agent reads it: hidden instructions, invisible text and links that leak data.

Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.

High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation

Scans RAG content/scraped pages for indirect prompt injection

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.

Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.

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

Scans RAG content/scraped pages for indirect prompt injection

Dynamic SQL AST taint tracking and static vulnerability auditor detecting tautology injections

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

Mindstone-internal release-pipeline test connector; not for use. Single ping tool; no auth.

Multi-CI security scanner with a live threat-intel feed of compromised CI components

Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.

Payment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection.