ClawHub
Back to skill

Security audit

Qase

Security checks for vulnerabilities and agentic risk

Overview

This Qase skill is a clearly disclosed connector that uses the OOMOL oo CLI for Qase reads and user-confirmed writes.

Install this only if you want Codex to operate Qase through your OOMOL-connected account. Review write payloads carefully before approving them, and treat first-time setup commands as account/CLI setup steps that should only be run when needed.

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
92% confidence
Finding
The skill description says to use this skill for "ANY Qase request" and "Whenever a task involves Qase," which creates an overly broad trigger surface. This can cause the agent to invoke the skill on ambiguous mentions of Qase, leading to unintended reads or prompting toward write-capable operations in contexts where the user did not explicitly request connector use.

Static analysis

No suspicious patterns detected.