Loading ToolBench

Reading the current corpus…

agent-shield MCP server · F · ToolBench

agent-shield

github.com/Subsonic-control636/agent-shield

Multi-engine AI agent security scanner — detects backdoors, data exfiltration, prompt injection, tool poisoning, and supply chain attacks in AI agent skills, MCP servers, and plugins

2026-07-28+STDIO0 tools

28/100

Definition Quality0

Protocol Readiness0

Supportability46

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Summary

Scoring was not performed

Score history

Overall score trend

First recorded score · v2 rubric

28/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	28	2026-07-28+	v2