Clinical Data Cleaner

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:34 PM UTC
• Version: 1.0.0

Overview

This skill is a local clinical data cleaning tool whose file access and outputs fit its stated purpose, with dependency and validation cautions but no evidence of hidden or malicious behavior.

Install only in an environment appropriate for sensitive clinical data. Confirm the input file, output path, and cleaning options before running, avoid overwriting raw datasets, review the generated audit report, and pin vetted versions of numpy, pandas, and scipy for any regulated or repeatable workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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 (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill documentation advertises executable workflows that read input files and write cleaned datasets and audit reports, but it does not declare corresponding permissions. In an agent environment, this creates a trust and policy gap: operators may approve or route the skill under the assumption that it has no file-system effects, while the packaged code is expected to access and modify local data.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy
pandas
scipy

• Confidence: 97% confidence
• Finding: The dependency is unpinned, so installs may resolve to different versions over time, harming reproducibility and potentially pulling in a newly introduced vulnerable or incompatible release. In a clinical data cleaning skill used for regulatory workflows, this increases supply-chain and validation risk because results and environments may drift between runs or submissions.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy
pandas
scipy

• Confidence: 97% confidence
• Finding: The pandas dependency is unpinned, which allows uncontrolled version changes during installation and can introduce vulnerable or behavior-changing releases. For regulated clinical data processing, this is especially risky because reproducibility, auditability, and consistent outputs are important operational and compliance requirements.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy
pandas
scipy

• Confidence: 97% confidence
• Finding: An unpinned scipy dependency creates a supply-chain and reproducibility weakness because future installs may fetch different versions with new defects or security issues. In a clinical-trial data context, nondeterministic environments can undermine trust in transformed datasets and validation evidence.

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: 87% confidence
• Finding: The file permits installation of numpy without any version restriction, so dependency resolution may select a release affected by known advisories or permit unsafe downgrade scenarios. Because this skill processes clinical data in potentially sensitive and regulated environments, exposure to vulnerable scientific libraries raises both security and integrity concerns even if exploitation may depend on specific usage paths.

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: 79% confidence
• Finding: Pandas is listed without a version, which can allow installation of releases associated with published advisories, including disputed ones. Although exploitability may depend on unsafe deserialization patterns not shown here, leaving the package unconstrained in a data-processing skill unnecessarily increases attack surface and operational 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 unversioned, allowing installation of versions with known security issues such as insecure temporary directory behavior in older releases. In a clinical data processing environment, vulnerable scientific packages can threaten system integrity or data handling security, especially on shared or automated processing hosts.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.