ClawHub
Back to skill

Security audit

Agenty

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Agenty connector skill that uses the OOMOL oo CLI for user-directed Agenty actions, including clearly labeled write and destructive operations.

Install only if you intend to let Codex operate your Agenty account through OOMOL. Review write or destructive requests carefully before approving them, especially list clearing, row deletion, and agent deletion. The clean VirusTotal and static scan results support the benign verdict, but the skill still grants meaningful account-level action authority when you approve those operations.

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
90% confidence
Finding
The trigger description is extremely broad: it instructs the agent to use this skill for ANY Agenty request instead of calling the API directly. That can cause unintended invocation whenever Agenty is merely mentioned, increasing the chance of unnecessary tool use, accidental data access, or state-changing operations being routed through the skill without sufficient task-specific gating.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.