ClawHub
Back to skill

Security audit

muapi-cinema-director

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward video-prompt helper that calls an external video-generation backend for the requested creative task.

Before installing, understand that video briefs and generated cinematic prompts may be sent to muapi.ai and downstream video providers. Avoid including secrets, private personal data, or proprietary material unless you are comfortable sharing it with those services.

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)

Missing User Warnings

Low
Confidence
97% confidence
Finding
The skill instructs agents to send user-provided creative briefs to external video-generation providers via muapi.ai and downstream model vendors, but it does not warn users that their prompt content will leave the local environment. This creates a real privacy and data-handling transparency issue because users may include confidential, proprietary, or personal information in prompts without informed consent.

Missing User Warnings

Low
Confidence
78% confidence
Finding
The script invokes a downstream shell script via `bash "$CORE_SCRIPT"` and uses `--async`, which causes an external action to run without any confirmation prompt or explicit user-facing notice beyond the internal comment. For code files, subprocess execution can warrant a finding when there is no visible disclosure in code, and this line has no print/log/confirmation informing the user that generation is being dispatched asynchronously.

Static analysis

No suspicious patterns detected.