Back to skill

Security audit

Pans Gpu Solution Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward GPU configuration calculator with an optional user-directed file export, and I found no hidden network, credential, persistence, or destructive behavior.

Install this only if you want a Chinese-language GPU planning helper. When using --output, provide a workspace-local filename you are comfortable creating or overwriting, and independently verify the GPU pricing and sizing assumptions before using the recommendations for purchasing or budgeting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill advertises code-driven behavior that can write output files (--output solution.md) but does not declare any tool scope or permission boundaries. In an agent environment, undeclared file-write capability can lead to unauthorized file creation or overwriting, especially if user-controlled paths are accepted.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad and generic, such as 'GPU推荐', '配置推荐', and 'solution builder', which can cause the skill to activate on common requests not specifically intended for it. Overbroad activation increases the chance the skill handles unrelated prompts and performs file-writing or recommendation logic in contexts where it was not expected.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This Python file includes natural-language descriptions, docstrings, CLI help text, and output text exclusively in Chinese, which effectively forces a specific language for users. The file does not offer an opt-in language selection or explain that the skill is intentionally limited to a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest frames the skill as a GPU solution builder that recommends configurations and outputs Markdown or JSON. In code, the optional --output parameter causes the tool to create or overwrite an arbitrary file path, which is behavior beyond simply generating a recommendation in-memory or to stdout.

Content

No source excerpt is available for this finding.