Loading ToolBench

Reading the current corpus…

SENTINEL MCP server · F · ToolBench

SENTINEL

Static security scanner for AI agent configuration files. Detects prompt injection, hidden instructions, and malicious directives in CLAUDE.md, AGENTS.md, .cursorrules, MCP configs, and other agent-facing files.

2026-07-28+STREAMABLE_HTTP0 tools

27/100

Definition Quality0

Protocol Readiness0

Supportability45

Spec posture

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

Static source inference · medium confidence · evidence: Streamable HTTP

Current-spec patterns detected

Summary

Scoring was not performed

Score history

Overall score trend

First recorded score · v2 rubric

27/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	27	2026-07-28+	v2