ClawHub

academic-literature-ppt

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed academic-paper-to-Chinese-slide workflow with no executable code or hidden data access.

Install this if you specifically want academic papers converted into Chinese-language PPTX presentations. If you need English, bilingual output, source-language preservation, or a different slide style, state that explicitly when using the skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger description is broad enough to activate on generic requests for slides, reports, or summaries, which can cause the wrong skill to be selected outside its intended academic-literature context. In practice this can override user intent, force inappropriate transformations such as literature-style formatting or Chinese translation, and increase the chance of mishandling unrelated uploaded content.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill description mandates Chinese-translated output without any user opt-in, which can cause unauthorized language transformation of source content and produce outputs the user did not request. This is especially risky for academic material because translation can alter nuance, terminology, or compliance expectations, and may conflict with user needs for original-language fidelity.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
Fixing the primary language to Chinese at the reference-source level bakes in a non-optional behavior that may transform all processed literature regardless of user preference or source language. In an academic summarization skill, this can lead to inaccurate or unusable outputs, especially when precise technical wording or citation-adjacent context matters.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal