论文精读翻译

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ArXiv paper translation workflow that can upload results to IMA and Tencent Docs, so users should confirm uploads but the behavior matches its purpose.

Install this only if you want ArXiv-paper translations prepared for IMA and Tencent Docs. Avoid using it for private manuscripts or restricted notes unless you are comfortable uploading the resulting Markdown and images, and ask the agent to confirm before any upload or token configuration step.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrases include broad everyday-language requests such as '帮我翻译' and 'translate paper', which can cause the skill to activate in contexts beyond ArXiv paper translation. Overbroad invocation increases the chance of accidental routing of unrelated or sensitive content into a workflow that fetches, processes, and may upload data to external platforms.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs uploading translated content to IMA knowledge base and Tencent Docs but provides no user-facing warning, consent step, or data-classification check before transmission. That creates a real risk of sending copyrighted, confidential, or sensitive user-provided material to third-party services without clear authorization.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal