ClawHub
Back to skill

Security audit

Hookdeck

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Hookdeck management integration that can change or delete Hookdeck resources, but it clearly scopes those actions and requires confirmation for risky operations.

Install only if you want an agent to manage Hookdeck through an OOMOL-connected account. Review proposed payloads carefully before approving writes, and treat delete actions as irreversible Hookdeck changes.

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
87% confidence
Finding
The skill description says to use this skill for ANY Hookdeck request, which can cause overly aggressive routing whenever Hookdeck is merely mentioned. In an agent setting, this increases the chance of invoking a state-changing integration without sufficient task disambiguation, especially because the skill exposes write and destructive actions alongside read actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.