Tag

#agent-security

MCP servers, skills and plugins tagged “agent-security” on GitHub.

33 entries · real GitHub data

#31Helm AI Kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
MCP server AI & LLM tooling Memory & knowledge
#32Little Canary
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the…
MCP server AI & LLM tooling Security
#33Prism Scanner
Open-source security scanner for AI Agent skills, plugins & MCP servers. 39 detection rules. pip install prism-scanner
MCP server Security AI & LLM tooling