ClawHub
Back to skill

Security audit

Encharge

Security checks across malware telemetry and agentic risk

Overview

This Encharge skill is a disclosed connector for sending transactional email through OOMOL, with clear write-action confirmation guidance and no evidence of hidden or destructive behavior.

Install only if you intend to let the agent use your connected OOMOL/Encharge account. Because it can send transactional email, review the recipient, subject, body, and payload before approving any write action, and treat the broad 'any Encharge request' wording as routing guidance rather than permission for automatic sends.

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
95% confidence
Finding
The description says to use this skill for ANY Encharge request and instead of calling the API directly, which creates an overly broad trigger surface for automatic invocation. That can cause the agent to route unrelated or insufficiently scoped Encharge tasks through a write-capable skill, increasing the chance of unintended external actions such as sending emails without strong contextual checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.