ClawHub
Back to skill

Security audit

Attention

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Attention connector skill for reading and analyzing Attention data through OOMOL, with no hidden scripts or destructive behavior found.

Install this only if you want your agent to access Attention through your OOMOL-connected account. Because returned conversations, users, teams, and analysis results can contain sensitive business information, ask for narrow filters, specific IDs, or clear scopes when using it.

SkillSpector

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
90% confidence
Finding
The skill description says to use this skill for "ANY Attention request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to invoke the skill in situations where a narrower or more appropriate path should be chosen. Because the skill can access organizational conversation and user data, unintended invocation may expose sensitive information or cause unnecessary data access beyond the user's actual intent.

Static analysis

No suspicious patterns detected.