ClawHub
Back to skill

Security audit

Celigo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Celigo connector wrapper that uses OOMOL's oo CLI and does not show hidden, destructive, or deceptive behavior.

Install only if you intend to let an agent use your OOMOL-connected Celigo account. Review requested Celigo actions and payloads before approving anything tagged write or destructive, and avoid using the skill for general Celigo questions that do not need account access.

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
82% confidence
Finding
The phrase instructing use for "ANY Celigo request" is overly broad and can cause the agent to invoke this skill whenever Celigo is merely mentioned, even if the user's intent is informational or unrelated to executing account actions. In an agentic environment, ambiguous triggers increase the chance of unintended tool use against a live connected account.

Static analysis

No suspicious patterns detected.