ClawHub
Back to skill

Security audit

TheHive

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TheHive connector with write actions gated by user confirmation, though users should understand it can create TheHive cases and alerts.

Install only if you want agents to access your OOMOL-connected TheHive instance. Review write payloads carefully before approving case or alert creation, and only complete the OOMOL/TheHive connection for accounts with appropriate permissions.

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
93% confidence
Finding
The description says to use this skill for "ANY TheHive request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to route all TheHive-related tasks through this skill without sufficient task-specific scoping. In a high-privilege incident-response system like TheHive, this increases the chance of unintended write operations, misuse in ambiguous contexts, or over-reliance on a connector path that may bypass safer, more explicit decision logic.

Static analysis

No suspicious patterns detected.