Back to skill
Skillv1.0.1
ClawScan security
EdrawMax Skills · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 13, 2026, 2:07 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code, instructions, and resources are coherent with its stated purpose (calling EdrawMax AI endpoints and downloading returned images); it requests no credentials and includes a safe, domain-restricted downloader script.
- Guidance
- This skill appears coherent and does what it says: it calls EdrawMax's documented endpoints and saves returned PNG/SVG files locally using the bundled Python script. Before installing, confirm you trust the EdrawMax API domain (https://api.edrawmax.cn) and are comfortable that user prompts/descriptions will be sent to that external service (no credentials are required). Ensure the agent environment has Python available to run the download script and that network access to the API and the EdrawMax OSS domains (.aliyuncs.com, .wondershare.com, .edrawsoft.com, .edrawmax.com) is permitted. If you have privacy concerns, avoid sending sensitive data in prompts because the service processes the prompt server-side.
Review Dimensions
- Purpose & Capability
- okName/description (diagram generation) align with the SKILL.md and included files: API endpoints, expected responses, and a downloader script are all directly related to generating and saving diagrams. No unrelated credentials, binaries, or install steps are requested.
- Instruction Scope
- okRuntime instructions are specific: determine diagram type, POST to documented EdrawMax endpoints, and run the included download script to save PNG/SVG locally. The SKILL.md does not instruct the agent to read unrelated files, access irrelevant env vars, or transmit data to third parties beyond the stated EdrawMax API and trusted OSS domains.
- Install Mechanism
- okNo install spec (instruction-only) and the only code included is a small Python downloader script. Nothing in the manifest downloads or executes code from arbitrary URLs or third-party package registries.
- Credentials
- okThe skill declares no required environment variables or credentials and the instructions do not reference any secrets. The API is documented as not requiring auth. The downloader uses system TLS verification and only accepts a short, justified set of trusted hostname suffixes.
- Persistence & Privilege
- okThe skill does not request persistent system privileges, always:false, and does not modify other skills or global agent config. It only writes image files into a user-controlled output directory.