Differential Gene Expression Analysis (RNA-seq)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:26 PM UTC
• Version:
  1.0.1

Overview

This is a small RNA-seq analysis skill whose main risks are disclosure gaps around input data and package installation, not evidence of malicious behavior.

Before installing, expect the skill to read input/count_matrix.csv and to download/install R/Bioconductor packages if they are not already present. Use a project-specific or disposable R environment if package changes matter, and avoid placing sensitive count data in the input path unless you are comfortable having it processed locally.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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 (3)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill description claims it uses simulated expression data, but the code actually processes a user-supplied CSV and installs packages from the network at runtime. This mismatch can mislead users about both data handling and execution behavior, increasing the chance they run untrusted code or expose sensitive data under false assumptions.

Intent-Code Divergence

Medium

• Confidence: 97% confidence
• Finding: The markdown states the analysis uses simulated expression data, but the implementation reads input/count_matrix.csv, meaning real user-provided data is processed. This is a security-relevant documentation deception because users may treat the skill as self-contained and safe when it actually ingests external data that may be sensitive or malformed.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The skill installs R/Bioconductor packages from the network at runtime without disclosing this behavior. Runtime dependency installation expands the attack surface through supply-chain compromise, unexpected code execution during package install, and non-reproducible environments, especially in automated agent execution contexts.

VirusTotal

63/63 vendors flagged this skill as clean.