Not measured4 / 6 checks passed
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
- Updated recently
Not checked yet
GuardBeeVerified
io.github.GuardBee
The registry namespace is a GitHub login.
Repositories
Servers
- Not measured4 / 6 checks passed
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
KVKK/GDPR/CCPA compliance checks for codebases
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
CVE scanning for npm/pip/cargo dependencies via OSV
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
DNS record enumeration, misconfiguration and dangling-subdomain detection
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Finds PII and credentials in PDFs, screenshots and scanned documents
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans agent code for untrusted input poisoning persistent cross-session memory
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans ML model files (PyTorch, joblib, NumPy, GGUF, TensorFlow…) and HF repos for supply-chain risks
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans RAG content/scraped pages for indirect prompt injection
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Catches leaked credentials and PII in outbound LLM prompts
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Audits shipped apps for how easily they can be reverse engineered
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Baselines an MCP server's tools and detects tool-definition changes after approval
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans files for leaked secrets and API keys
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Checks declared npm/PyPI dependencies against real registries to catch slopsquatting
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
TLS certificate/cipher/protocol inspection
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
Finance & CryptoPayments & trading
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Developer ToolsAI / LLM tooling
- Updated recently
Not checked yet
- Not measured4 / 6 checks passed
Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
- Updated recently
Not checked yet