Back to skill

Security audit

Pans Gpu Calculator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local GPU sizing and cost calculator with no evidence of hidden data access, network use, persistence, or unsafe behavior.

Install this if you want a Chinese-language local calculator for GPU deployment estimates. Treat the built-in prices and formulas as rough planning assumptions and verify them before purchasing capacity; broad GPU-related trigger phrases may cause the skill to activate for general GPU cost or sizing questions.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is broad and generic, covering common GPU and cost-planning phrases without clear activation boundaries. This can cause the skill to activate in unrelated conversations about GPUs, deployment, or cost estimation, increasing the chance of unintended tool use or user confusion even though the skill itself is not overtly harmful.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring, help text, examples, and console output are written entirely in Chinese, which imposes a specific language on users. The file does not provide any opt-in, fallback, or justification for this locale restriction, matching the policy's language/locale violation criterion.

Content

No source excerpt is available for this finding.