EasyEDA API Skill

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

The skill appears purpose-built for EasyEDA, but it gives the agent broad live control of your EasyEDA client and projects through a local code-execution bridge.

Install this only if you intentionally want an AI agent to control EasyEDA. Back up important projects, verify the companion EasyEDA extension, confirm the selected EDA window, require approval before edits or destructive actions, keep the bridge local, and stop the background server when done.

Findings (5)

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.

What this means

An agent using this bridge could inspect or change the active EasyEDA project, schematic, PCB, libraries, or other client state if it sends mutating code.

Why it was flagged

The skill exposes a generic code execution endpoint into the running EasyEDA client. This is central to the skill, but it is broad authority and the shown instructions do not define approval, read-only defaults, or operation-level limits.

Skill content
curl -X POST http://localhost:${BRIDGE_PORT:-49620}/execute ... -d '{"code": "return await eda.dmt_Project.getCurrentProjectInfo();"}'
Recommendation

Use only with trusted agents and projects, keep backups, require explicit confirmation before edits/deletes/publishing, and prefer scoped helper commands over arbitrary code execution where possible.

What this means

The agent may act with your EasyEDA permissions in the selected window, even though the skill does not request separate credentials.

Why it was flagged

The bridge operates inside the user's active EasyEDA client, so actions inherit whatever project, library, workspace, or account permissions that client has.

Skill content
Execute code in the running EasyEDA Pro client ... including PCB design, schematic editing, footprint/symbol management, and project operations.
Recommendation

Confirm the active EasyEDA window and account before use, and avoid running the bridge while sensitive or unrelated projects are open.

What this means

Installing the companion extension expands the trusted code involved in controlling EasyEDA.

Why it was flagged

The documented workflow depends on an external EasyEDA extension in addition to the local skill files. This is purpose-aligned, but users must trust that extension source.

Skill content
Install the `run-api-gateway.eext` extension in EasyEDA Pro. Download link: https://ext.lceda.cn/item/oshwhub/run-api-gateway
Recommendation

Install the extension only from the official/expected publisher, verify the version, and remove or disable it when not needed.

What this means

Code and results may pass through the bridge, and incorrect or unintended local connections could matter if the bridge is reachable beyond the intended agent/client pair.

Why it was flagged

The bridge uses local HTTP/WebSocket discovery and a service-name handshake to connect the agent and EasyEDA client. The shown documentation does not describe stronger authentication or per-session authorization.

Skill content
Both AI and EDA clients auto-discover the server by scanning the port range and verifying a handshake (`service: "easyeda-bridge"`).
Recommendation

Ensure the bridge binds only to localhost, add or verify a per-session token if available, and stop the bridge after the EasyEDA session.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The local bridge may keep running and remain able to accept EasyEDA automation requests until stopped.

Why it was flagged

The skill explicitly starts a long-running background bridge process. This is disclosed and fits the purpose, but it can remain available after the immediate task.

Skill content
The bridge server must run in the background ... node ${CLAUDE_SKILL_DIR}/scripts/bridge-server.mjs &
Recommendation

Stop the Node bridge process when finished, especially before opening unrelated EasyEDA projects.