Back to skill

Security audit

Product Design Team — Agent Configuration Bundle

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed frontend product-design skill with broad but purpose-aligned build permissions and no hidden code or persistence mechanism.

Install this only if you want an agent team that can modify frontend files and run local build or review commands. Keep it pointed at a specific workspace or repository, and review shell commands and memory use if your environment contains sensitive project data.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is described only as turning a product brief into designs and a built frontend, but it does not define clear activation boundaries, allowed targets, or prohibited actions. In a multi-agent setup with file-writing and shell execution capabilities, ambiguous scope increases the chance the skill is invoked for adjacent or unsafe tasks, leading to unintended code changes or command execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Multiple roles are granted file_write and shell_exec, but the skill description does not prominently warn users that using the skill can modify files and run local commands. That omission can cause users or orchestrators to invoke the skill without understanding it has code execution and filesystem mutation power, increasing the risk of unsafe or over-broad use.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
80% confidence
Finding

The phrase 'Not limited to React' and support for 'any future surface' weakens the skill's boundaries and signals open-ended expansion beyond a defined technology stack. In context, that broad mandate combines with shell execution and file writing to make it easier for the agent to justify operating across unexpected environments, increasing the chance of scope creep and unsafe actions.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
| Role | Purpose | Tools |
|---|---|---|
| `ui-ux-designer` | UI/UX design authority. Owns the design system, produces visual assets, maintains cross-surface consistency, and writes all user-facing microcopy and templates. | file_read, file_write, shell_exec, web_search, memory_store, memory_recall |
| `frontend-builder` | Cross-surface frontend builder. Implements UI for web, desktop, mobile, VS Code extension, Chrome extension, and any future surface. Not limited to React. | file_read, file_write, file_list, shell_exec, memory_store, memory_recall |
| `project-manager` | Project manager and resource orchestrator. Owns the task backlog, sprint planning, dependency mapping, team coordination, and agent lifecycle management (spawn, pause, stop). | file_read, file_write, memory_store, memory_recall, task_post, task_claim |
| `reviewer` | Pipeline reviewer. Reviews proposed changes for correctness, maintainability, tests, and release readiness. | file_read, file_list, memory_store, memory_recall, agent_send |

Static analysis

No suspicious patterns detected.