ClawHub
Back to skill

Security audit

Omise

Security checks for vulnerabilities and agentic risk

Overview

This Omise skill is coherent and mostly transparent, but it tells the agent to install a required CLI by running a remotely fetched shell script, which users should review carefully before allowing.

Install only if you are comfortable connecting Omise through OOMOL and letting the agent run oo CLI actions against that account. Review or manually install the oo CLI from a trusted source before allowing the remote install command, and require explicit confirmation for customer updates or deletions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
98% confidence
Finding
The skill instructs the agent to install software by piping a remotely fetched script directly into a shell, which creates a supply-chain and arbitrary code execution risk. If the remote host, transport, or script content is compromised, the agent could execute attacker-controlled code with the user's privileges.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description defines invocation in extremely broad terms rather than with specific trigger phrases or boundaries. This can cause unintended activation for any mention of Omise-related work, with no negative examples or exclusion conditions to narrow scope.

Static analysis

No suspicious patterns detected.