Security audit

Adobe Automator

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly discloses that it runs arbitrary Adobe ExtendScript, but that is high-impact local automation with weak execution safeguards.

Install only if you specifically need raw Adobe ExtendScript automation and are prepared to review every script before it runs. Do not use it with scripts from documents, websites, chats, or other untrusted sources; a safer version should add explicit confirmation, scoped script templates, and hardened temporary file handling.

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

Error

Location: handler.js:68
Finding: Predictable and Non-Exclusive Temporary Files Allow File Overwrite and Script Substitution
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest describes a generalized Adobe automation capability across multiple powerful desktop applications without defining clear trigger boundaries, permitted actions, or activation constraints. In a skill that can drive Photoshop, Illustrator, InDesign, Premiere Pro, and After Effects, this broad scope increases the chance of over-privileged or unintended automation being invoked in contexts the user did not expect.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The command accepts arbitrary JSX from ctx.params.script, writes it to a temporary file, and executes it in a local Adobe application via cscript/osascript with no validation, consent gate, or sandboxing. ExtendScript can access the filesystem and interact with host applications, so any upstream prompt injection or untrusted input reaching this command can become local code-like execution with user-level impact.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: handler.js:81