Back to skill

Security audit

Thesis Literature Review Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Chinese academic literature-review writing aid with no code execution, persistence, credential access, or hidden data handling.

Install this if you want help drafting Chinese thesis literature review sections. Users should still verify all citations, replace placeholders with real sources, and ensure the output matches their school's academic integrity and formatting rules.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction says to use the skill only to write the literature review part of a Chinese academic paper and sets the default output as a polished Chinese section. This imposes a specific language requirement without indicating that the user may choose another language or explicitly opt in, which matches the locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file requires that the writing should be formal Chinese academic prose, which forces a specific language/locale in the skill behavior. Because no language choice or opt-in is offered here, this is a natural-language policy violation under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata and default prompt hard-code Chinese output without confirming the user's language preference, which can override user intent and create deceptive or unusable output in multilingual contexts. This is especially risky in academic settings where language requirements, citation conventions, and audience expectations vary, so forced output can lead to incorrect submissions or hidden prompt-routing behavior the user did not request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The default invocation phrase is generic enough that it can be triggered in situations beyond a narrowly scoped literature-review request, increasing the chance of accidental activation or misuse. In agent ecosystems, overly broad trigger wording can route unrelated academic-writing tasks into this skill, causing inappropriate autonomous content generation and reducing user control over when the skill is invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L484 states that the prose must be in formal Chinese academic style. Under the policy, forcing a specific language or locale is a violation unless the skill offers user choice or clearly documents a justified region-specific constraint, which this file does not do.

Content

No source excerpt is available for this finding.