10 actions in 3 pieces of software · ranked by words, meaning and measured trust · 630 ms

1. 1RelayShield Agentic Attack Surfaceverified and signedpassport

   MCP serverrecord

   • relayshield_agentic_attack_surface_check_tech_stack_cve

     Check a declared AI agent framework / tech stack for CISA KEV or high-EPSS CVEs actively being exploited. Covers AI agent orchestration frameworks (LangChain, CrewAI, AutoGPT, Flowise, n8n self-hosted) and common companion infrastructure (Nacos, MinIO). Returns: A structured result: outcome/recommen

   • relayshield_agentic_attack_surface_check_prompt_injection_breach

     Check an email address for credential exposure sourced specifically from prompt-injection attacks against AI agents, distinct from ordinary phishing/malware-sourced breaches. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

   • relayshield_agentic_attack_surface_check_bulk_identity_risk

     Hierarchical org + AI-agent-identity risk scoring for a domain and up to 5 agent/service-account identities. A critically-exposed agent automatically elevates the organizational risk rating. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

   • relayshield_agentic_attack_surface_check_agent_risk_summary

     Composite risk check -- one call instead of four. Runs breach exposure, LLM credential exposure, and tech-stack CVE checks together and returns a single fused risk verdict, so a calling agent doesn't have to make multiple tool calls and reason about how to combine their results itself. Returns: A st

   • relayshield_agentic_attack_surface_check_session_risk

     Check an email for active or reusable stolen session material (cookies, tokens) found in criminal stealer logs — exposure that can bypass MFA/authentication entirely, not just a password. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

   • relayshield_agentic_attack_surface_check_supply_chain

     Check up to 10 vendor domains for breach and infostealer exposure — third-party and supply-chain risk inherited through vendor relationships. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

2. 2RelayShield Agentic Attack Surface (AWS Marketplace)verified and signedpassport

   MCP serverrecord

   • relayshield_agentic_attack_surface_aws_check_tech_stack_cve

     Check a declared AI agent framework / tech stack for CISA KEV or high-EPSS CVEs actively being exploited. Covers AI agent orchestration frameworks (LangChain, CrewAI, AutoGPT, Flowise, n8n self-hosted) and common companion infrastructure (Nacos, MinIO). Returns: A structured result: outcome/recommen

   • relayshield_agentic_attack_surface_aws_check_prompt_injection_breach

     Check an email address for credential exposure sourced specifically from prompt-injection attacks against AI agents, distinct from ordinary phishing/malware-sourced breaches. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

   • relayshield_agentic_attack_surface_aws_check_bulk_identity_risk

     Hierarchical org + AI-agent-identity risk scoring for a domain and up to 5 agent/service-account identities. A critically-exposed agent automatically elevates the organizational risk rating. Returns: A structured result: outcome/recommended_action plus evidence and reason codes.

3. 3agentic-bug-hunterfound in code, not yet checkedno passport yet

   MCP serverawarexone/agentic-bug-hunter

   • bughunter_attack_surface

     Summarize existing recon artifacts for a target (passive, local files only).