ClawHub
Back to skill

Security audit

Permit.io

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed Permit.io connector that can read and modify Permit.io data, with explicit confirmation requirements for writes and deletes.

Install only if you want an agent to manage Permit.io through your OOMOL-connected account. Review any proposed create, update, role assignment, unassignment, or delete payload carefully before approval, especially tenant, user, and role targets. Treat the oo CLI install and OOMOL account connection as normal setup steps that grant the connector access to your Permit.io environment.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The trigger description is extremely broad: it instructs use of this skill for ANY Permit.io request and for any task involving Permit.io. That can cause the agent to invoke a state-capable integration in situations where a narrower read-only or more specialized skill would be safer, increasing the chance of unintended writes, deletes, or disclosure through over-selection.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.