Security audit

Academic Paper Mentor

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only academic writing mentor skill with disclosed, purpose-aligned web and memory use, though its broad Chinese triggers may activate more often than some users expect.

Install this if you want a Chinese-language academic paper mentor. Be mindful that it may activate on broad paper-related prompts, and avoid storing sensitive unpublished research details in memory unless you are comfortable with cross-session retention.

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The natural-language description is written as a Chinese-only instruction and the file consistently presents the skill as operating in Chinese, but it does not state that this language constraint is optional or user-selectable. Under the policy, forcing a specific language without user opt-in is a locale/language policy concern.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger list contains broad, common academic phrases such as '写论文', '学术写作', and '文献综述' that are likely to appear in ordinary user requests outside the intended scope. This can cause unintended activation of the skill, routing users into a rigid workflow or exposing tool-enabled behavior when a general assistant response would have been more appropriate.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The startup keyword list includes especially vague phrases like '帮我看看论文', which can match routine requests for proofreading or feedback rather than explicit use of this specialized skill. Unintended activation increases the chance of misrouting, incorrect assumptions about user goals, and unnecessary access to associated tools or memory features.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown case study presents all instructions and interaction content in Chinese, with no indication that users can opt into another language or that the skill is intentionally region- or language-specific.