ClawHub
Back to skill

Security audit

Emelia

Security checks across malware telemetry and agentic risk

Overview

This is a narrow Emelia read-only connector skill with disclosed setup and credential handling, though users should be aware it can read account campaign and contact data when invoked.

Install only if you want Codex to use your OOMOL-connected Emelia account to read campaign, contact, provider, and webhook information. For casual or ambiguous Emelia mentions, ask the agent not to query the connector unless you explicitly request account data.

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
91% confidence
Finding
The trigger text instructs use of this skill for ANY Emelia request and whenever a task involves Emelia, which is overly broad and can cause the agent to invoke the skill on casual mentions or ambiguous requests rather than only when the user clearly intends Emelia data access. In a connector skill that can enumerate account data, unintended invocation may expose metadata or perform unnecessary authenticated queries without sufficient user intent validation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.