ClawHub
Back to skill

Security audit

MarketTime

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed MarketTime connector for reading account data, with some broad routing language users should apply carefully.

Install this only if you want your agent to access your connected MarketTime account through OOMOL. Use it for explicit catalog, manufacturer, or order lookups, and require confirmation before any future write or destructive MarketTime action even if the connector exposes one.

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
95% confidence
Finding
The manifest promises a read/search-only skill, but the body explicitly allows running any MarketTime action and describes handling for `[write]` and `[destructive]` operations. This mismatch can cause an orchestrator or user to treat the skill as read-only when it may invoke state-changing connector actions, increasing the risk of unintended modifications.

Intent-Code Divergence

Low
Confidence
83% confidence
Finding
The skill states that untagged actions are safe reads, but it also instructs the agent to inspect live connector schemas before execution, implying available actions may vary dynamically outside the static list. If the connector exposes new or mislabeled actions, the agent could rely on an unsafe safety model and execute operations that are not actually read-only.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The instruction to use this skill for ANY MarketTime request is overly broad and can cause the agent to route even incidental mentions of MarketTime through the connector. That increases the chance of unnecessary external data access, user-intent confusion, and accidental execution in contexts where the user did not ask to interact with the connected account.

Static analysis

No suspicious patterns detected.