ClawHub
Back to skill

Security audit

OpenClaw Email Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrow ClawHub staff workflow for drafting, sending, and recording content-rights case emails, with explicit review and signoff steps.

Install only for staff who are authorized to handle ClawHub content-rights cases and send official correspondence. Users should verify the CHR case, recipient, subject, and body before approving any send.

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 description says to use the skill whenever an AI agent needs to 'plan, review, implement, audit, or improve email work' and then says 'Triggers include requests about' several topics. Although examples are provided, the activation scope remains broad and lacks explicit exclusion conditions beyond the later markdown guidance, which may cause unintended invocation for ordinary email tasks.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.