A2A Auditor MCP
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
github.com/GuardBee · 32 listed services · provider site
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
KVKK/GDPR/CCPA compliance checks for codebases
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
CVE scanning for npm/pip/cargo dependencies via OSV
DNS record enumeration, misconfiguration and dangling-subdomain detection
MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Scans agent code for untrusted input poisoning persistent cross-session memory
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
Scans RAG content/scraped pages for indirect prompt injection
Catches leaked credentials and PII in outbound LLM prompts
Baselines an MCP server's tools and detects tool-definition changes after approval
Scans files for leaked secrets and API keys
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence
Checks declared npm/PyPI dependencies against real registries to catch slopsquatting
TLS certificate/cipher/protocol inspection
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
Finds PII and credentials in PDFs, screenshots and scanned documents
Provider identity is derived from the domain or repository in the source record. If two vendors share a host, they appear together here — that is a limitation of the data, not a statement about ownership.