ClawHub

方洪波思维视角 v2.0

Security checks across malware telemetry and agentic risk

Overview

This appears to be a persona-style management skill with broad trigger wording, but no evidence of hidden actions, credential use, persistence, or system changes.

Install this only if you want a Fang Hongbo-style management perspective to appear in relevant business discussions. Be aware that generic management phrases may invoke it unintentionally, so users should disable or narrow triggers if they want explicit opt-in behavior only.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list includes generic business terms such as “职业经理人”, “战略定力”, and “组织重构”, which are broad enough to match many normal enterprise conversations unrelated to this specific skill. This can cause unintended invocation, confusing skill routing and potentially surfacing proprietary or opinionated behavior when the user did not explicitly request it.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains broad generic phrases such as business and management terms that could appear in ordinary conversation, causing unintended activation of the skill. In a persona-style skill, accidental invocation can steer the assistant into a constrained viewpoint without explicit user intent, which may degrade response reliability and user control.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal