Caveat verdict

openclaw-admin-main

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Administrative dashboard for OpenClaw deployment management; no capabilities, content describes standard admin functionality with no evidence of malicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
80
transparency
80
maintenance

Findings (13)

Pattern match high

<script> tag in markdown — potential code injection

AGENTS.md · prose · downgraded · <script

Pattern match high

Possible hardcoded credential

src/i18n/messages/zh-CN.ts · prose · downgraded · secret: '输入新值(留空不变更)

Pattern match medium

Opens WebSocket connection

DYNAMIC_AGENTS_FIX_SUMMARY.md · code · WebSocket

Pattern match medium

Accesses OpenClaw config/secrets directly

DYNAMIC_AGENTS_USER_GUIDE.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Uses exec() — may execute shell commands

server/database.js · prose · downgraded · exec(

Pattern match medium

Base64 decode (atob) — may hide malicious payloads

src/api/device-identity.ts · prose · downgraded · atob(

Pattern match medium

References sudo — requests elevated privileges

src/i18n/messages/zh-CN.ts · prose · downgraded · sudo

Pattern match medium

Dynamic import() — loads module at runtime

src/router/routes.ts · prose · downgraded · import('

Pattern match low

Base64 encode (btoa) — may obfuscate data exfiltration

src/api/device-identity.ts · prose · downgraded · btoa(

Pattern match low

String.fromCharCode — can build strings to evade detection

src/api/device-identity.ts · prose · downgraded · String.fromCharCode

Pattern match low

queueMicrotask — defers execution via microtask queue

src/api/http-client.ts · prose · downgraded · queueMicrotask(

Pattern match low

References agent configuration files

src/api/types/config.ts · prose · downgraded · AgentConfig

Pattern match low

References agent memory files

src/stores/memory.ts · prose · downgraded · MEMORY.md

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API