ClawHub
Back to skill

Security audit

Vibe Creating Prompt

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only prompt-rewriting skill for video prompts, with no code execution, persistence, credential access, or hidden data handling.

Install this only if you want an agent to rewrite or clean up creative video prompts. Be aware it may demote or translate technical camera parameters unless you explicitly ask to keep them, and for mixed-language prompts you may want to state the desired output language.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 140)May include surrounding context.

md
- **Multi-shot experience** — for multi-segment, multi-scene, multi-cut input that serves one shared experience. Break by natural segments (or by number only if the user asked). 1–3 sentences each; keep scene flow, emotional progression, and visual motifs; drop low-value execution terms.
- **Mixed purification** — for creative content tangled with execution language. Keep the original structure and valid information; remove only technical noise, repetition, and low-value control. Don't over-rewrite or invent new beats.

## Output Rules

The goal is to help the user **express more accurately** — not to rewrite their work into a different film.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs output to be produced 'in the target language' without defining how that language is chosen or confirming it with the user. In practice, this can cause unintended language switching, misinterpretation of user intent, or prompt corruption when mixed-language inputs contain safety-relevant constraints such as dialogue or instructions that must be preserved verbatim.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.