ClawHub
Back to skill

Security audit

Video Prompt Reverse Engineer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only guide for analyzing videos and writing AI video prompts, with no executable code, persistence, credential use, or hidden data handling found.

Before installing, be aware that the skill may steer HappyHorse prompts toward Chinese for better model results. Use it with user-provided media or descriptions, and ask for the original language to be preserved when translation 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes a language requirement ('Write prompts in Chinese for best results') for HappyHorse without checking the user's language preference or obtaining opt-in. This can cause unintended data transformation, reduce transparency, and lead the agent to override user intent or mishandle sensitive input by translating it into another language before submission to a third-party model.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown reference repeatedly states that Chinese prompts are supported, recommended, preferred, or better for certain models and workflows. That can be read as steering users toward a specific language/locale without offering a user choice or documenting a justified locale-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.