Skillv1.0.2

ClawScan security

企业微信 AI Bot 对接 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 15, 2026, 9:17 AM

Verdict: Benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's files and runtime instructions are coherent with its stated purpose (adding a 企业微信/WeCom bot to the local OpenClaw config); it only edits the local OpenClaw configuration and does not attempt network exfiltration or request unrelated credentials.
Guidance: This skill appears to be what it says: it updates your local OpenClaw configuration to add a 企业微信 AI Bot. Before running it: (1) inspect scripts/setup_wecom.py yourself (it's short and readable) to confirm behavior; (2) ensure your ~/.openclaw directory is the correct OpenClaw config and back it up; (3) protect the saved Secret — the script writes it into the config in plaintext, so restrict file permissions (e.g., chmod 600) and do not commit the config to version control; (4) prefer dmPolicy allowlist in production; (5) if you don't trust the package source, manually add the config entries instead of running the script. If you want lower risk, run the script with --bot-id and --secret only after review or apply the config changes by hand.

Purpose & Capability: okName/description promise (configure OpenClaw ↔ 企业微信 AI Bot) matches the provided assets: SKILL.md describes the steps and the included script updates ~/.openclaw/openclaw.json. No unrelated binaries, env vars, or services are requested.
Instruction Scope: okSKILL.md instructs the user to create an AI Bot in 企业微信, run the included Python script to insert Bot ID/Secret into the OpenClaw config, and restart the gateway. The instructions reference only local config files, OpenClaw commands, and vendor docs. The script prompts for credentials but does not transmit them elsewhere. Note: the skill stores the secret in the OpenClaw config file in plaintext (expected for local channel config), so protect that file.
Install Mechanism: okNo install spec or remote downloads are present; the skill is instruction-only plus a small included Python script. Nothing is fetched from external URLs during installation.
Credentials: okThe skill requests no environment variables or external credentials beyond what the user provides interactively (Bot ID and Secret). Those credentials are directly required for the integration and are justified by the purpose.
Persistence & Privilege: okThe skill does not request always-on inclusion and does not alter other skills or system-wide settings beyond writing to the user's OpenClaw config file (its stated purpose). Autonomous model invocation defaults are unchanged.