v1.0.0

快速配置新的agent

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:06 AM.

Analysis

This skill mostly matches its stated purpose, but it deserves review because it stores Feishu bot secrets, changes OpenClaw routing configuration, and restarts the Gateway service.

GuidanceReview this before installing or running. It appears purpose-aligned, but it will persist Feishu credentials, edit ~/.openclaw/openclaw.json, alter routing behavior, and restart Gateway. Use a restricted DM policy where possible, verify the target agent/chat binding carefully, and keep the automatic backup for rollback.

Findings (3)

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.

Abnormal behavior control

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.

Tool Misuse and Exploitation

SeverityHighConfidenceHighStatusConcern

index.js

saveConfig(config); ... execSync('openclaw config set session.dmScope "per-account-channel-peer"', { stdio: 'pipe' }); ... execSync('openclaw gateway restart', { stdio: 'inherit' });

The code writes the OpenClaw config, changes session routing behavior, and restarts Gateway after arguments are provided. These actions are purpose-aligned and disclosed, but they are high-impact and not guarded by code-level confirmation.

User impactA mistaken or unintended run could change which agent receives Feishu messages and briefly interrupt Gateway service.

RecommendationRun it only after reviewing the generated account, routing mode, agent ID, and chat ID; keep the backup and be prepared to restore the OpenClaw config if routing is wrong.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

package.json

"dependencies": { "readline": "^1.3.0" }

The package declares an external semver-ranged dependency even though the provided code does not appear to require it. This is not evidence of malicious behavior, but it is unnecessary supply-chain surface if dependencies are installed.

User impactInstalling dependencies could fetch extra package code that is not needed for the shown implementation.

RecommendationPrefer running from reviewed source without installing unnecessary dependencies, or remove/lock unused dependencies before installation.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusConcern

index.js

appSecret: appsecret, ... dmPolicy: options.dmpolicy || 'open', allowFrom: ['*'], enabled: true

The skill persists a Feishu App Secret and defaults the account to an open/wildcard inbound policy. That is expected for bot setup, but it is sensitive account authority and broad by default.

User impactAnyone allowed by that Feishu bot policy may be able to send messages that get routed to the chosen OpenClaw agent, and the App Secret will remain in local configuration.

RecommendationUse the least-permissive DM policy that works, verify who can message the bot, and protect the OpenClaw config file that stores the App Secret.