解决方案专家

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  1.0.0

Overview

This skill is a coherent proposal/PPT-outline helper with expected file and PPT-generation behavior, but users should verify any local converter scripts before using PPT export.

Install is reasonable for drafting Chinese-oriented solution narratives and PPT-ready JSON. Before using PPT export, make sure the workspace's referenced Python generator and template files are trusted, because they are executed or consumed locally but are not included in this skill package.

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
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill description is broad enough to capture many ordinary writing, analysis, proposal, and presentation tasks, which can cause inappropriate auto-invocation outside a narrowly scoped use case. Over-broad routing increases the chance the agent will access files or generate artifacts when the user did not clearly intend to use this specific skill.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs the agent to read local files and later write JSON/PPT outputs as part of the normal workflow, but it does not require explicit user confirmation, file-path constraints, or disclosure that local workspace data will be accessed and new files created. In an agent environment, this can lead to unintended data exposure from unrelated local documents or unwanted filesystem side effects.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: Forcing a Chinese-only content structure without user choice can cause the skill to ignore user language preferences or transform content into an unintended language. This is primarily a safety and usability issue because it may produce misleading deliverables, obscure review by the user, or mishandle multilingual source material.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The schema and default deck values hard-code Chinese text, which can override the user's requested language and reduce transparency when outputs are consumed by non-Chinese readers. While not directly enabling code execution or data exfiltration, it can still create integrity issues in business documents and increase the risk of user misunderstanding.

VirusTotal

66/66 vendors flagged this skill as clean.