ClawHub
Back to skill

Security audit

Emailable

Security checks for vulnerabilities and agentic risk

Overview

This Emailable skill is mostly a normal connector wrapper, but it under-labels a batch verification action that creates remote jobs and may consume credits.

Install only if you are comfortable letting agents use your connected Emailable account through OOMOL. Before any batch verification, require explicit confirmation of the exact email list and expected credit or billing impact; treat `verify_batch_emails` as a write action even though the skill does not label it that way.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest and description claim the skill is limited to searching and reading data, but the documented actions include `verify_batch_emails`, which creates a batch verification job and therefore changes remote state. This mismatch can mislead an agent or user into invoking a write-capable skill under the assumption it is read-only, weakening consent and safety controls.

Intent-Code Divergence

High
Confidence
99% confidence
Finding
The safety guidance states that untagged actions are reads, yet `verify_batch_emails` is untagged even though it creates a new batch job. This is dangerous because agents may auto-execute it without confirmation based on the misleading rule, causing unintended processing, cost consumption, or remote side effects.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The instruction to use this skill for 'ANY Emailable request' is overly broad and can trigger the skill for loosely related mentions, even when direct use is unnecessary or a safer workflow exists. Overbroad routing increases the chance of unintended tool invocation, especially given the skill exposes a write-capable action that is mislabeled as read-safe elsewhere.

Static analysis

No suspicious patterns detected.