Science Agent Recommend - Find the Right AI Tool for Research

• Outcome: Pass
• Latest audit: May 29, 2026, 8:37 PM
• Version:
  1.0.0

Overview

This is a low-risk recommendation skill that only provides curated links to science AI tools.

Safe to install as a directory-style recommender. Treat the linked third-party projects separately and review them before installing or granting access to credentials, local files, clinical data, or research datasets.

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: 93% confidence
• Finding: The trigger phrases include broad natural-language requests such as 'best AI for research' and 'help me find a research tool', which could match many ordinary conversations and cause the skill to activate unintentionally. This is not a direct code-execution issue, but it can lead to incorrect routing, unexpected disclosure of the skill’s content, or user confusion when the assistant invokes this directory-style skill in contexts where it was not requested.

VirusTotal

65/65 vendors flagged this skill as clean.