星芒答辩评委

• Outcome: Pass
• Latest audit: May 28, 2026, 10:29 AM
• Version:
  1.0.0

Overview

This is a Chinese academic defense practice skill that only guides conversation, asks tailored questions, and gives scores and feedback without hidden access or executable behavior.

Reasonable to install if you want a Chinese academic defense rehearsal assistant. Avoid pasting confidential or unpublished research unless you are comfortable sharing it in the agent session, and be aware that broad Chinese defense-related wording may trigger this structured practice mode.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger conditions are broad and partly ambiguous, such as activating on general mentions of '答辩' or when a user '主动要求答辩评委帮助'. This can cause unintended invocation in unrelated contexts, leading to context confusion, inappropriate responses, or unexpected handling of user-provided academic content.

Natural-Language Policy Violations

Medium

• Confidence: 81% confidence
• Finding: The skill is written entirely in Chinese with no language choice or opt-in, which can create usability and consent issues for users who do not read Chinese. In security terms this is mainly a safety and accessibility weakness: users may trigger or interact with the skill without understanding its behavior, limits, or scoring logic.

VirusTotal

64/64 vendors flagged this skill as clean.