Security audit

Thesis Writing Advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only thesis-planning helper with no code execution, persistence, credential access, or hidden data handling.

Install only if you want a thesis-planning assistant that may produce substantial Chinese-language proposal and chapter-outline text. Users should still check school academic-integrity rules, verify citations, and review any psychology or participant-safety guidance with an advisor.

A.I.G

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

SkillSpector

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 (7)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is very broad and overlaps heavily with generic thesis-help, psychology-topic, proposal, and writing-guidance requests. In a skill-routing system, this can cause the skill to be invoked for a wide range of common academic-writing prompts, increasing unintended activation and the chance that users are steered into full-paper generation, policy-sensitive academic assistance, or lower-quality routing decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The default prompt uses a very broad activation phrase tied to common academic-writing requests, which can cause the skill to trigger for ordinary user intents that only loosely match the skill scope. This increases the chance of unintended invocation, confusing routing, or accidental disclosure of the skill’s specialized behavior in contexts where the user did not explicitly request it.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The file requires a fixed Chinese section title and note, which effectively forces output in Chinese. This is a natural-language locale policy issue because the skill does not offer opt-in, user choice, or a documented justification for restricting language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The guide hardcodes Chinese output structures and example phrasing without indicating that this is conditional on user language preference. In a bilingual skill, this can override or disregard the user's chosen language, causing instruction-priority conflicts, degraded usability, and potentially unsafe misunderstandings if users cannot accurately review or validate academic guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: These lines instruct the skill to produce proposal sections and research questions in Chinese terms such as "推荐题目", "研究目的", and question forms like "如何" and "怎样理解". Because the file does not provide an opt-in or alternative language path, it imposes a specific language/locale in a way that can violate language-choice policy.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The instruction to default to Chinese when the user asks in Chinese imposes a language behavior automatically rather than explicitly offering the user a choice. Under the stated policy, language or locale constraints should either be user-selected or clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Line L013 instructs conversion into a specific Chinese phrase ("方案设计依据"), and many subsequent recommended titles are given only in Chinese. This can amount to a locale/language constraint in the skill content without explicit user opt-in or a documented region-specific justification in the file.
Content: No source excerpt is available for this finding.