Multi-Omics Integration Strategist

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:31 PM UTC
• Version: 1.0.0

Overview

This is a local bioinformatics analysis skill that reads user-provided omics CSV files and writes local result files, with no evidence of hidden network access, credential use, persistence, or destructive behavior.

Install this in a virtual environment, consider pinning dependency versions before use, and treat both input omics datasets and generated outputs as sensitive local research data. Choose the output directory intentionally because the script will create files there.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The manifest documents that the skill reads inputs and writes multiple outputs, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users or orchestrators may underestimate the file-write capability, and missing explicit permission declarations can weaken sandboxing or approval flows.

Intent-Code Divergence

Medium

• Confidence: 86% confidence
• Finding: The security checklist asserts protections such as path validation and output-directory restriction, but no supporting code is provided. In a skill that accepts file paths and writes outputs, absent or unverified path controls can enable path traversal or unintended writes outside the workspace, especially if users supply crafted --output or input paths.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

dataclasses
networkx
numpy
pandas
scipy

• Confidence: 88% confidence
• Finding: `networkx` is specified without a version constraint, so installs may pull different releases over time, including versions with newly disclosed vulnerabilities or breaking behavior. This is a real supply-chain hardening weakness, though not an immediately exploitable bug by itself.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

dataclasses
networkx
numpy
pandas
scipy
sklearn

• Confidence: 97% confidence
• Finding: `numpy` is unpinned, and this is more concerning because the same file also flags `numpy` as having known advisories. Without pinning, environments may resolve to vulnerable or incompatible versions, increasing supply-chain and dependency-risk exposure for a data-processing skill.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

dataclasses
networkx
numpy
pandas
scipy
sklearn

• Confidence: 96% confidence
• Finding: `pandas` is unpinned, which is a genuine security hygiene issue here because known advisories exist for some versions. An unconstrained install can silently select a vulnerable release, especially across different environments or over time.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

networkx
numpy
pandas
scipy
sklearn

• Confidence: 96% confidence
• Finding: `scipy` is unpinned, and the package has known historical advisories, so unconstrained resolution can expose users to vulnerable versions. This creates avoidable supply-chain risk in an analysis-oriented skill that is likely to be installed in research or shared compute environments.

Known Vulnerable Dependency: numpy — 10 advisory(ies): CVE-2014-1859 (Numpy arbitrary file write via symlink attack); CVE-2021-41495 (NumPy NULL Pointer Dereference); CVE-2021-33430 (NumPy Buffer Overflow (Disputed)) +7 more

Critical

• Category: Supply Chain
• Confidence: 93% confidence
• Finding: The file declares `numpy` with no version, and the analyzer reports multiple advisories affecting some NumPy releases. Because no safe version is constrained, installations may resolve to versions with memory-safety or file-write issues, which can be significant in environments processing untrusted data or running shared workloads.

Known Vulnerable Dependency: pandas — 1 advisory(ies): CVE-2020-13091 (** DISPUTED ** pandas through 1.0.3 can unserialize and execute commands from an)

High

• Category: Supply Chain
• Confidence: 71% confidence
• Finding: The `pandas` advisory cited is disputed and often depends on unsafe deserialization patterns in consuming code, so the package entry alone does not prove direct exploitability. However, because no version is pinned, the requirements still permit potentially affected versions, making this a real but context-dependent dependency risk.

Known Vulnerable Dependency: scipy — 4 advisory(ies): CVE-2013-4251 (SciPy creates insecure temporary directories); CVE-2013-4251 (The scipy.weave component in SciPy before 0.12.1 creates insecure temporary dire); CVE-2023-25399 (A refcounting issue which leads to potential memory leak was discovered in scipy) +1 more

High

• Category: Supply Chain
• Confidence: 90% confidence
• Finding: `scipy` is included without a version restriction, and the analyzer lists several historical vulnerabilities affecting some SciPy versions. In a scientific computing skill, this is a real dependency risk because users may install an older vulnerable version, particularly in long-lived research environments.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.