Back to skill

Security audit

Shangan Gongkao

Security checks for vulnerabilities and agentic risk

Overview

This is a focused Chinese civil-service exam study skill that reads relevant local study materials and does not show hidden, persistent, destructive, or credential-related behavior.

Install this only if you want an assistant to use your local Chinese public-exam preparation folder as source material. Review the configured folder path and keep unrelated private documents out of that folder if you do not want them considered.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
91% confidence
Finding

The activation scope is broad enough to overlap with generic study-planning, summarization, checklist, and note-organization requests, which can cause the skill to trigger outside its intended niche. Overbroad routing can expose local-material access behavior in contexts where it is unnecessary, increasing the chance of unintended file inspection or confusing tool use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill is written entirely around Chinese-language interaction and exam-domain assumptions without stating whether other user languages are supported or how to handle language preference. This can lead to poor consent and usability outcomes, such as forcing responses in Chinese or misrouting users who ask in another language, though it is not directly a code-execution or data-exfiltration issue.

Content

No source excerpt is available for this finding.