m5stack-assistant
Analysis
This is a coherent M5Stack documentation helper that uses a disclosed remote MCP lookup service and optional Node.js helper scripts, with no evidence of credential access, persistence, or destructive behavior.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Source: unknown; Homepage: none ... Required binaries (all must exist): none ... No install spec — this is an instruction-only skill. Code file presence: 3 code file(s)
The registry metadata does not provide an upstream source/homepage or declare Node as a requirement, even though helper scripts are included; the visible code is small and purpose-aligned, so this is a transparency note rather than a concern.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
端点: `https://mcp.m5stack.com/sse` ... 发送JSON-RPC请求: POST 到返回的 `/messages?session_id=xxx` 端点
The skill intentionally uses a remote MCP/SSE service for documentation lookup, so M5Stack-related query text is transmitted to that service.
