Security audit
OpenClaw Feishu Reasoning UX
Security checks across malware telemetry and agentic risk
Overview
This is a coherent instruction-only skill for improving OpenClaw Feishu message cards, with disclosed cautions around logs, session state, backups, rollback, and restarts.
Install this only if you want OpenClaw Feishu card/reasoning customization. Before using it, verify the GitHub source, approve any edits to OpenClaw runtime/session files, require backups and rollback steps, and avoid enabling raw reasoning in Feishu chats where private prompts or model reasoning should not be visible.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.