Remotion视频工作室

• Outcome: Review
• Latest audit: Aug 20, 2026 · 4:54 AM UTC
• Version: 1.0.0

Overview

This video-generation skill mostly matches its stated purpose, but it also introduces under-scoped API, callback, file, and command-execution behavior that users should review before installing.

Install only if you are comfortable with an agent running local Remotion/npm commands and writing project files. Treat callback URLs and third-party API keys as sensitive: use them only when needed, confirm the exact endpoint and data being sent, and keep any credentials in environment variables rather than project files.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

• Confidence: 91% confidence
• Finding: The skill states that it does not require API keys, but later instructs users to configure API keys and establish API connections as part of normal use. This inconsistency can mislead users and agents about the trust boundary, increasing the risk that secrets are entered, stored, or transmitted to external services without clear necessity or informed consent.

Intent-Code Divergence

Medium

• Confidence: 87% confidence
• Finding: The document frames the skill as a Markdown-based local Remotion rendering tool, but later presents generic external API integration as a core capability. That mismatch obscures what the skill is actually allowed to do and may cause an agent or user to approve networked behavior they did not expect, expanding the attack surface beyond local video generation.

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: Later sections broaden the skill from a specific Remotion video tool into a generic automation tool for file processing, API usage, and command execution. In an agent context with exec/read/write tools, this kind of scope expansion is dangerous because it can normalize unrelated privileged actions and make it easier to justify arbitrary filesystem, network, or shell operations under the guise of the skill.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill accepts a callback URL but does not clearly warn that user data, processing results, or metadata may be transmitted to that URL. In agent workflows, undocumented callbacks can lead to silent exfiltration of sensitive prompts, generated content, filenames, or operational metadata to attacker-controlled endpoints.

Missing User Warnings

Low

• Confidence: 81% confidence
• Finding: The instructions describe command execution and writing output files without a clear warning about system-side effects such as process execution, package invocation, disk writes, and resource consumption. While expected in a rendering skill, the lack of upfront disclosure can cause users or agents to authorize actions without understanding local impact, especially when exec is available.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.