ClawHub
Back to skill

Security audit

preview-outcome

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for creating temporary RooQuiz preview personality quizzes, with the external upload clearly disclosed.

Install only if you are comfortable sending the quiz content you create to RooQuiz/Quizster to generate a temporary preview link. Avoid putting secrets or sensitive personal data into preview quiz text, images, or CTA URLs, and specify your preferred language if English is not desired.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
For example, with `curl` (write the JSON to a file first, or inline it with `--data`):

```bash
curl -sS -X POST https://preview.rooquiz.com/api/preview-forms \
  -H 'Content-Type: application/json' \
  --data-binary @/tmp/preview-form.json
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The file states `language: "en_US"` while noting the platform default is `zh_CN`, and later instructs the agent to 'just choose a random' theme when the user has no preference, but it does not offer a comparable user choice for language. Because supported language values are explicitly listed later, hardcoding a specific locale in the documented skill flow can violate language-choice policy when the user has not opted into English.

Static analysis

No suspicious patterns detected.