Search: "malicious"

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

TweetFeed collects Indicators of Compromise (IOCs) shared by the infosec community at Twitter. Here you will find malicious URLs, domains, IPs, and SHA256/MD5 hashes.

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.