ClawAudit verdict
飞书多 Agent 配置助手
feishu-multi-agent-manager
Interactive wizard to configure multiple Feishu bot agents within OpenClaw; no sensitive data exfiltration, no remote code execution, and behavior fully matches the stated multi-agent setup purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
README.md · code · Secret: 'main_secret_xxx
Data URI with base64 payload — may embed malicious content
dist/index.js · prose · downgraded · data:application/json;base64,
Long base64 string (100+ chars) — likely obfuscated payload
dist/index.js · prose · downgraded · eyJ2ZXJzaW9uIjozLCJmaWxlIjoiaW5kZXguanMiLCJzb3VyY2VSb290IjoiIiwic291cmNlcyI6WyIu
References agent memory files
dist/index.js · prose · downgraded · MEMORY.md
References agent configuration files
src/index.ts · prose · downgraded · AgentConfig
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.