Back to skill

Security audit

Facetory 表盘开发

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Facetory watchface workflow that uses a local Facetory MCP server and a read-only diagnostic script, with sensitive root-file-copy steps gated by explicit user permission.

Install this only if you intend to let an agent operate your active Facetory watchface project through the local Facetory MCP server. Review any planned edits or exports before applying them, and only approve root commands when you understand the exact source file, destination, overwrite behavior, and risk.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description presents a full-featured Facetory integration for operating on Xiaomi/Redmi/Mi Band watchface projects. The supplied code only performs a connectivity/health diagnostic against the local MCP server by calling initialize and tools/list. Its primary purpose is server discovery and diagnostics, not project manipulation. While the description briefly mentions diagnosing the built-in server, that is only a small subset of the claimed functionality, and the code does not implement the core described capabilities.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill describes capability to connect to a built-in MCP server and even run a local Python connectivity check, but it does not declare an explicit tool scope such as allowed-tools or permissions. That creates an authorization ambiguity where an agent may invoke networked or external-capability tools without a clear least-privilege boundary, increasing the chance of unintended access or side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow explicitly recommends using root privileges to copy files into the app's private directory when normal access fails, but it does not include strong safety constraints, risk warnings, or verification steps. In an agent-driven workflow, this can normalize privileged filesystem operations and lead to accidental modification of protected app data, corruption of projects, or misuse of root access on the host device.

Content

No source excerpt is available for this finding.