潮汐调研框架

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This is an instruction-only deep research workflow that asks for web research and citation discipline, without installs, credentials, persistence, or hidden data access.

Installers should expect this skill to take over broad research/report requests and use web research. Avoid feeding it proprietary or sensitive topics unless the agent environment and browsing tools are appropriate for that data. The missing referenced templates may affect formatting quality but do not indicate unsafe behavior.

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 (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger list is very broad and includes generic phrases such as 'research report', '调研', and '分析一下XX行业/市场/技术', which can match many ordinary user requests and cause unintended skill activation. In an agent setting, over-broad invocation can route users into a rigid workflow unexpectedly, increasing the chance of prompt hijacking, misuse of tools, or inappropriate handling of tasks outside the skill's intended scope.

VirusTotal

64/64 vendors flagged this skill as clean.