ClawHub
Back to skill

Security audit

Psd Automator Skill Command

Security checks for vulnerabilities and agentic risk

Overview

This skill is a thin command wrapper for PSD automation, with local file changes that match its stated purpose but should be used carefully.

Install only if you intend to use the existing psd-automator workflow. Prefer --dry-run for unfamiliar tasks, review which PSD and output path will be used, and avoid running broad natural-language requests against sensitive design files unless you trust the underlying psd-automator core.

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
  • 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)

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The argument syntax uses `中文需求` and the only concrete example is written in Chinese, which suggests the skill expects or favors Chinese input. The file does not state that other languages are supported, offer a language choice, or justify a China-specific restriction.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly describes modifying a PSD and exporting a PNG to the local desktop, but the documentation does not warn users that invoking it can change existing files or create new local outputs. In a user-invocable command that accepts raw task input, lack of disclosure increases the risk of unintended file changes, overwrites, or privacy exposure through exported assets.

Static analysis

No suspicious patterns detected.