飞书知识库查询

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Feishu/OpenClaw knowledge-base lookup guide with no install hooks, persistence, or privileged local behavior.

Install this if you want the agent to consult OpenClaw Feishu documentation during relevant tasks. Because some trigger phrases are broad, clarify when you do not want a Feishu knowledge-base lookup or when you only mean the current conversation history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad enough to match routine requests like '参考之前' or '确认一下之前的操作', which can cause this skill to activate outside its intended scope. Over-broad activation can steer the agent toward unnecessary knowledge-base queries, introduce irrelevant prior context into decision-making, and increase the chance of following stale or inappropriate documentation for the current task.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal