ClawHub

cai-chongxin-perspective-v2

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk, instruction-only business persona skill with broad activation and roleplay-style guidance but no system access or hidden behavior.

Install only if you want business and investment discussions framed through this simulated public-figure perspective. Be aware it may activate on broad finance or strategy topics, and avoid treating its outputs as verified professional advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
91% confidence
Finding
The skill uses broad scenario-based trigger phrases such as enterprise finance, M&A, international expansion, and long-term investing, which overlap heavily with ordinary business conversations. This can cause unintended activation, making the assistant adopt a persona and decision framework when the user did not explicitly request it, which may bias outputs and reduce reliability in unrelated contexts.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill prescribes a fixed language and stylistic profile, including first-person roleplay, specific rhetorical patterns, and a defined communication DNA, without offering user choice. While not directly harmful, this can misrepresent authorship, override user language preferences, and increase the chance of the model presenting stylized or persona-bound advice as authoritative.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal