Security audit

thesis-abstract-keyword-writer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only academic writing skill that helps draft thesis abstracts and keywords from user-provided material.

Safe to install for academic writing help. Users should still avoid pasting confidential thesis material unless they are comfortable sharing it with the agent environment, and should review the generated abstract for accuracy and school-specific formatting requirements.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
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 (2)

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations in natural-language instructions. Line L404 instructs the skill to use the thesis language by default, which imposes a language preference unless the user explicitly asks otherwise rather than offering an upfront choice.

Memory Manipulation

High

Category: Memory Poisoning
Content: - `摘要` and `关键词` for Chinese output, or `Abstract` and `Keywords` for English output - Bilingual abstract and keyword sections when requested or required - A standalone abstract that can be understood without reading the thesis - Clear statement of purpose, method, key findings, and contribution - Keywords that reflect the core topic and are not sentence fragments - Same language as the thesis unless otherwise requested
Confidence: 80% confidence
Finding: Clear state

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.