ClawHub
Back to skill

Security audit

Enormail

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent read-only Enormail connector, but its first-time setup tells an agent to install a CLI by executing a remote script without verification or explicit user approval.

Review the oo CLI installer before running it, prefer official/manual installation with verification where possible, and install this only if you are comfortable giving the OOMOL-connected account read access to Enormail data such as contacts, lists, senders, and mailing statistics.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill includes a shell one-liner that fetches a remote script over the network and immediately executes it with bash. This is dangerous because any compromise of the hosting domain, TLS termination, upstream distribution, or the script itself results in arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description instructs the agent to use this skill for ANY Enormail request, which is an overly broad trigger that can cause the skill to intercept tasks beyond its narrowly documented read/search purpose. Overbroad routing increases the chance that unrelated or higher-risk Enormail operations are funneled through this skill without sufficient user intent validation or least-privilege scoping.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.