ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

QQBot Multi-Account

v1.0.1

QQBot 多账号运维排障技能。用于 OpenClaw 多 Bot、多 Agent 场景下的账号绑定检查、重复会话诊断、主动发送与本地插件打包导出。触发词：QQBot多账号、双机器人、双Agent、账号绑定、重复会话、appId隔离。

⭐ 0· 314·1 current·1 all-time
by@naluko
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (multi-account QQBot diagnostics and plugin export) align with the provided scripts and docs. The skill inspects OpenClaw config, known-users, and packages a local qqbot extension — all expected for its stated troubleshooting/export purpose.
ℹ
Instruction Scope
The runtime instructions invoke two included shell scripts that: (a) read the OpenClaw config (default ~/.openclaw/openclaw.json) and print bindings/accounts and gateway port, and (b) tar the local qqbot extension directory (default ~/.openclaw/extensions/qqbot) into dist/. This stays within the troubleshooting/export scope, but scripts will reveal appId and clientSecretFile paths and can include any files present in the plugin directory (potentially secret files) in the generated archive.
✓
Install Mechanism
No install spec and no network download/install steps — instruction-only skill with bundled scripts. This is the lowest-risk install pattern and coherent with the declared skill type.
ℹ
Credentials
The skill declares no required env vars or credentials. The scripts do honor optional environment variables (QQBOT_SRC_DIR, QQBOT_EXPORT_DIR, QQBOT_KNOWN_USERS, OPENCLAW_CONFIG_PATH) but do not require external credentials. This is proportionate, though these env vars are not documented in SKILL.md as optional overrides (minor documentation gap).
✓
Persistence & Privilege
always is false and the skill does not request persistent/system-wide privileges. It does not modify other skills or agent configs. Autonomous invocation is allowed by default but not combined with other high-risk behaviors.
Assessment
This skill appears to do what it says: inspect local OpenClaw/qqbot configuration and create a tarball of the local qqbot extension. Before running: (1) review your OpenClaw config (~/.openclaw/openclaw.json) and any client secret files referenced by clientSecretFile to ensure you’re comfortable those paths will be printed or included, (2) understand that export-local-qqbot.sh packages the entire extension directory (QQBOT_SRC_DIR or ~/.openclaw/extensions/qqbot) which may contain secrets or credentials — move or remove sensitive files first or set QQBOT_SRC_DIR to a safe copy, (3) prefer running the scripts locally in a safe environment (they make no outbound network calls), and (4) consider setting QQBOT_EXPORT_DIR to a controlled location before exporting. If you want stronger assurance, inspect the plugin directory contents and the referenced secret file locations before using the export script.

Like a lobster shell, security has layers — review code before you run it.

latestvk973z7c4yv8yx0rbm4y7d3rjsh82shrn

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🤖 Clawdis

Comments