Back to skill

Security audit

GESP作业

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward GESP homework generator, with only minor activation-scope cautions.

Before installing, be aware that generic requests like creating practice papers may activate this skill; users should confirm the requested class, date, topic, and output path before letting it create files.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad phrases such as '出题' and '练习卷', which can match generic education-related requests beyond this skill's intended GESP scope. Overbroad activation can cause the wrong skill to engage, leading to prompt hijacking of unrelated tasks, unintended file generation, or leakage of contextual data into outputs that the user did not ask this skill to handle.

Content

No source excerpt is available for this finding.