Security audit

After Effects MCP

Security checks for vulnerabilities and agentic risk

Overview

This After Effects automation skill is mostly purpose-aligned, but its batch render script can write render outputs outside the intended folder when composition names are unsafe.

Review this skill before installing or using it. Only run the batch render script on trusted projects, avoid composition names containing path separators or '..', choose output folders carefully, and inspect the render queue output paths before starting a render. The issue is fixable by sanitizing composition names and confirming final output destinations.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/batch_render.jsx:8
Finding: Path Traversal Through Unsanitized Composition Names
Content: View full analysis
Remediation: View remediation
|\x00-\x1F]/g, "_"); safe = safe.replace(/\.\./g, "_"); if (safe === "" || safe === "." || safe === "..") { throw new Error("Invalid composition name for output"); } return safe; } var safeName = safeOutputName(compName); var outputDirectory = new Folder(outputPath); var destination = new File(outputDirectory.fsName + "/" + safeName + ".mov"); output.file = destination; ``` Because simple replacement alone may not cover every platform-specific path behavior, the implementation should additionally compare canonical paths and enforce that the final destination is contained within the approved output directory. ]]>

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: This markdown file includes examples for importing files, saving a project, and closing a project, but it does not warn users that these actions can modify project state or affect unsaved work. Under the markdown-specific missing-warning criterion, descriptions that cover potentially user-impacting operations should disclose those effects.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The Render Queue example sets an output file path and invokes rendering, which results in file creation on disk, but the markdown does not mention this behavior or its impact. For markdown skill documentation, file-affecting behavior should be disclosed when it may affect user data or system state.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.