ClawHub
Back to skill

Security audit

ExhibitDay

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing ExhibitDay, but it includes unsafe one-command installer instructions that execute remote code and broad account-changing capabilities that users should review carefully.

Review the installer step before using this skill. Prefer installing the oo CLI from a trusted package or official instructions you inspect yourself, and only allow create, update, or delete actions after confirming the exact ExhibitDay target and payload.

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)

Vague Triggers

High
Confidence
97% confidence
Finding
The skill description says to use this skill for ANY ExhibitDay request and to prefer it over direct API access, which is an overly broad routing trigger. That can cause the agent to invoke this skill in situations where narrower, safer, or more context-appropriate handling would be preferable, including operations that may lead to unintended writes or deletions. The risk is amplified because the same skill exposes both read and destructive actions.

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
99% confidence
Finding
The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (`curl ... | bash`). This is a classic supply-chain and remote code execution risk: if the remote host, transport, DNS, or install script is compromised, arbitrary code executes immediately on the user's machine. In a skill context, embedding this as a fallback setup step makes unsafe execution more likely.

Static analysis

No suspicious patterns detected.