Taste Paper

• Outcome: Pass
• Latest audit: Jun 17, 2026 at 9:56 AM UTC
• Version:
  0.1.0

Overview

This is a paper-review guidance skill with no executable code, persistence, credential access, or hidden data handling.

Install this if you want a strict, skeptical paper-triage assistant. Be aware it is written for Chinese output and may activate automatically in paper-review contexts; use explicit instructions if you want a different tone, language, or a less severe review.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The skill content is entirely in Chinese and instructs a fixed output style without offering any user language choice. This can override or conflict with a user's preferred language, reducing usability and potentially causing misunderstandings in high-stakes review workflows, though it is not a code-execution or data-exfiltration issue.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill enables implicit invocation while advertising a broad function, 'strict research-paper triage,' without narrow trigger constraints. This can cause the agent to activate the skill in unintended contexts involving papers, reviews, or comparisons, which may inject overly rigid judgments or bypass more appropriate user-directed behavior.

VirusTotal

62/62 vendors flagged this skill as clean.