ClawHub
Back to skill

Security audit

Trade Closer

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only skill for drafting B2B outreach emails, with no evidence that it sends messages, reads private data, or runs hidden code.

Reasonable to install for drafting B2B outreach. Users should confirm they intended a sales/outreach email skill when it activates, review any generated claims or performance numbers, and ensure messages comply with consent, anti-spam, and marketing rules before manually sending.

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
93% confidence
Finding
The trigger conditions are broad enough to match generic email-writing requests, which can cause the skill to activate when the user did not explicitly ask for this specific capability. That creates a scope/intent mismatch: the agent may steer ordinary writing tasks into outbound sales-email generation, producing unintended actions or content in contexts where the user expected a neutral assistant response.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.