Security audit

Test Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed creative media workflow skill that uses external AI/media providers and local rendering tools, with expected privacy and file-output considerations.

Install only if you are comfortable letting the agent use the provider API keys you set, potentially spend provider credits, send selected prompts/media to those services, and run local render/build tools. Use a separate project folder, set only the keys you intend to use, prefer dry-run or --provider when you want control, and avoid confidential or regulated media unless the chosen provider is approved.

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

Medium

Confidence: 90% confidence
Finding: The skill routes prompts, media, and other user-supplied content to multiple external providers, but the description does not clearly warn that this data leaves the local environment for API-backed processing. This can cause unintentional disclosure of sensitive text, images, or business assets if a user assumes the workflow is local-only.

Missing User Warnings

Low

Confidence: 87% confidence
Finding: The skill creates files, project directories, rendered media, task tracking logs, and potentially npm-based Remotion projects, but it does not prominently warn users about these filesystem changes. In shared or sensitive environments, generated artifacts may consume disk space, overwrite expected paths, or leave behind confidential media and metadata.

Static analysis

No suspicious patterns detected.