Back to skill

Security audit

Thesis Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese thesis-writing helper with no executable code or privileged behavior.

Install this if you want Chinese-language academic writing assistance for thesis drafting and organization. Review generated text carefully for factual accuracy, citation correctness, and consistency with your actual research data.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (3)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The system prompt explicitly instructs the assistant to reply in Chinese, which is a language-policy constraint expressed in natural language. The file does not indicate that the user can choose another language or opt in to this restriction, so it may violate locale/language choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This line says generated content defaults to a Chinese master's thesis writing style, which imposes a language/locale-specific output convention. Because the skill description does not present this as an optional preference or clearly justified regional constraint, it fits the policy-violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The interaction section states that the assistant uses Chinese by default and adds Chinese glosses for English terms. While a default can be acceptable, the file does not offer a user-selectable language option or clearly justify the restriction as region-specific, making this a natural-language policy concern.

Content

No source excerpt is available for this finding.