Back to skill

Security audit

Thesis Discussion Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Chinese academic-writing skill with no code execution, persistence, credential access, or hidden data movement.

Use this skill when you specifically want help drafting or polishing a Chinese thesis discussion section. Provide real findings and source context, because the skill is designed to avoid inventing results, citations, or conclusions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata and prompt mandate Chinese output without indicating that this is conditional on user preference or consent. This can override user language expectations, create usability and accessibility issues, and increase the chance of incorrect or unwanted output when the user did not request Chinese specifically.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default activation prompt is very broad and can be invoked for a wide range of writing requests without clear boundaries limiting it to discussion-only tasks. This increases the risk of misrouting user requests or causing the skill to generate content outside its intended scope, which can undermine policy controls and lead to unintended handling of unrelated academic writing tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and opening instruction specify a 'Chinese Discussion Chapter Writing Guide' and direct use for '第五章讨论' style output, which constrains the skill to Chinese-language content. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.