Back to skill

Security audit

Lab2startup Challenge Solutions

Security checks for vulnerabilities and agentic risk

Overview

This is a guidance-only Chinese skill for handling teacher-student startup collaboration challenges, with no tool use, credential access, network activity, or persistence.

This skill is appropriate to install if you want Chinese-language guidance for teacher-student startup collaboration problems. Users who prefer another language may need to ask the agent to translate or adapt the output.

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 (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is entirely in Chinese and specifies the skill's usage context and trigger phrases only in Chinese. This creates a language/locale constraint without any indication that users may interact in other languages or opt in to Chinese, which matches the policy category for forced language behavior.

Content

No source excerpt is available for this finding.