Sc-RNA Cell Type Annotator

• Outcome: Pass
• Latest audit: May 29, 2026, 8:33 PM
• Version:
  1.0.0

Overview

This is a small local single-cell RNA annotation helper with no evidence of hidden access, network use, persistence, or destructive behavior.

Install in a virtual environment and consider pinning pandas before use. Review the small script before running it on local research data, and only use it for scRNA marker-based cluster annotation with clear inputs such as cluster markers, species, and tissue context.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• 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

Findings (2)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The activation guidance is broader than the narrowly described skill purpose and invites use for generic data analysis tasks rather than only single-cell RNA cell-type annotation. In an agent setting, overly generic triggers can cause inappropriate activation, leading the agent to run local scripts or process files in contexts the user did not intend, which increases the chance of unsafe file access or misuse of the skill's execution surface.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

pandas

• Confidence: 98% confidence
• Finding: pandas

VirusTotal

66/66 vendors flagged this skill as clean.