ClawHub
Back to skill

Security audit

ablefy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-focused ablefy connector with some broad wording and generic safety/setup text, but no artifact evidence of hidden, destructive, or unrelated behavior.

Install this only if you want an agent to read ablefy account, product, and pricing-plan information through an OOMOL-connected account. Be aware that the trigger wording is broad, and first-time setup may ask you to install or authenticate the oo CLI if it is not already configured.

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
90% confidence
Finding
The manifest promises a read-only skill for 'searching and reading data', but the body instructs use of generic connector actions and explicitly discusses possible write and destructive operations. This mismatch can mislead downstream agents or reviewers into granting broader trust than warranted, increasing the chance of unintended auth/setup execution or future state-changing calls through the same skill.

Intent-Code Divergence

Low
Confidence
74% confidence
Finding
The skill lists only read actions, but its safety section is written as if write and destructive actions may be available. That inconsistency creates ambiguity about the connector's real capability set, which can cause an agent to overgeneralize and attempt unsafe operations if additional actions appear or are inferred from the generic guidance.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrase 'Use this skill for ANY ablefy request' is overly broad and encourages invocation whenever ablefy is merely mentioned, not only when the user's intent clearly requires this connector. Broad routing increases the chance of unnecessary tool use, accidental data access from a connected account, or bypassing more appropriate narrower skills or direct reasoning.

Static analysis

No suspicious patterns detected.