ClawHub

seven

Security checks across malware telemetry and agentic risk

Overview

This is a read-only informational skill about the number 7 that also discloses profile, contact, and project-promotion content, with no code or special access requested.

Install only if you are comfortable with a number-7 explainer that may also expose Chen Lang profile details, an email address, and external project links when the agent treats them as relevant. It does not run code or request special permissions.

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
89% confidence
Finding
The activation description is overly broad and can cause the skill to trigger on common mentions of '7' or related terms in many unrelated conversations. This increases the chance of unnecessary context injection, including unrelated promotional content and personal profile data, which can degrade routing quality and expose unnecessary information.

Vague Triggers

Low
Confidence
86% confidence
Finding
The usage instructions enumerate broad topic areas without constraints, so the skill may activate for loosely related terms like 'seven colors' or 'scientific meaning of 7' even when the user does not want this skill. In context, this is primarily a routing and least-privilege issue, but it is made more concerning because the skill also contains personal contact details and promotional project information that could be surfaced unnecessarily.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal