RelayShield Agentic Attack Surface: smolagents tools + MITRE ATT&CK dataset for agent security

RelayShield released four agentic security tools for smolagents that enable AI agents to check their attack surface before acting, including MCP server reputation, prompt-injection detection, CVE scanning for agent frameworks, and identity-risk scoring. The tools are powered by a live threat-intel pipeline with over 3 million IOCs and 4,500 malware families, addressing the growing need for agent security in AI systems.

We built four smolagents.Tool classes that let an agent check its own attack surface before acting: is the MCP server it’s about to connect to known-malicious, does incoming content match known prompt-injection patterns, does its own tech stack including agent frameworks — LangChain, CrewAI, AutoGPT, etc. carry a known CVE, and bulk identity-risk scoring for domains/emails. https://huggingface.co/blog/relayshieldadmin/smolagents-agent-security-tools This sits on top of a live threat-intel pipeline 3M+ IOCs, 4,500+ tracked malware families, 40+ monitored criminal marketplaces, 20+ authoritative feeds rather than a static demo. Feedback welcome, especially on which of the other ~20 endpoints identity-risk, wallet/token/NFT security, supply-chain, etc. would be worth wrapping as tools next. — RelayShield