strain identification

• Outcome: Review
• Latest audit: May 29, 2026 · 9:24 PM UTC
• Version: 1.0.0

Overview

The skill fits an online BLAST report workflow, but it uploads sequencing data to NCBI and appears to generate reports from hard-coded identification results, so users should review it before use.

Install only after reviewing the code. Do not use it for proprietary, clinical, regulated, or confidential sequences unless your organization permits uploading them to NCBI. Treat its identification output as unreliable until real BLAST result retrieval and parsing are implemented, and run it in a dedicated folder to avoid overwriting an existing report.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The code transmits raw biological sequence data to NCBI over the network via requests.post without any consent prompt, disclosure, or configuration to disable external sharing. Even though NCBI uses HTTPS, sequence data may still be sensitive, proprietary, or regulated, so silent exfiltration to a third-party service creates a real confidentiality and compliance risk.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill uses a generic "text" trigger without any activation phrase, scope restriction, or context guardrails. This can cause the skill to activate on unrelated user input and unexpectedly process local file paths or initiate downstream actions, which increases the attack surface and the chance of unsafe or unauthorized execution.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly states it will submit sequencing data to the online NCBI BLAST service, but it does not disclose that user-provided biological sequence data leaves the local environment and is transmitted to a third party. This can create privacy, confidentiality, and compliance risks, especially if the samples are sensitive, proprietary, clinical, or otherwise regulated.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

biopython>=1.81
python-docx>=0.8.11
requests>=2.31.0

• Confidence: 95% confidence
• Finding: The dependency is specified with only a lower bound, which allows future unreviewed versions to be installed and makes builds non-reproducible. This increases supply-chain risk and can unexpectedly introduce vulnerable or breaking releases into the skill environment.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

biopython>=1.81
python-docx>=0.8.11
requests>=2.31.0

• Confidence: 98% confidence
• Finding: The package is unpinned and also corresponds to a library with known historical XXE issues, so allowing any version above a minimum broadens the chance of resolving to an unsafe or incompatible release. This creates reproducibility and supply-chain exposure, especially for document-processing code that may parse attacker-controlled files.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

biopython>=1.81
python-docx>=0.8.11
requests>=2.31.0

• Confidence: 98% confidence
• Finding: Using requests with only a minimum version allows dependency resolution to select versions with known advisories or future unvetted releases. Because requests commonly handles outbound HTTP and credentials, non-reproducible version selection can materially increase the attack surface.

Known Vulnerable Dependency: biopython — 1 advisory(ies): CVE-2025-68463 (Biopython is vulnerable to doctype XML external entity (XXE) injection through B)

Low

• Category: Supply Chain
• Confidence: 76% confidence
• Finding: Biopython is flagged for a published XXE-related advisory, and the requirement allows versions at or above 1.81 rather than explicitly excluding affected releases. If the skill processes attacker-controlled biological/XML-like data formats through vulnerable parsing paths, this could enable file disclosure, SSRF, or parser abuse.

Known Vulnerable Dependency: python-docx — 2 advisory(ies): CVE-2016-5851 (Improper Restriction of XML External Entity Reference in python-docx); CVE-2016-5851 (python-docx before 0.8.6 allows context-dependent attackers to conduct XML Exter)

High

• Category: Supply Chain
• Confidence: 99% confidence
• Finding: python-docx has a well-known XXE vulnerability in older versions, and the declared constraint '>=0.8.11' does not guarantee safety unless the exact installed version is controlled. If the skill opens untrusted DOCX files, XXE could lead to local file disclosure, server-side request forgery, or related XML parser attacks.

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High

• Category: Supply Chain
• Confidence: 90% confidence
• Finding: requests is associated with multiple advisories, including credential leakage and TLS/session verification issues in some versions, while the requirement remains broadly unpinned. In a skill context, HTTP client libraries often process secrets, tokens, and external URLs, so installing an affected version can expose sensitive data or weaken transport security.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.