Security audit

疾病最新药物研究报告

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed biomedical research helper that runs local Python adapters to query public drug and clinical-trial data, with routine cautions around third-party searches and unpinned dependencies.

Before installing, treat it like a biomedical research tool that can run bundled Python scripts and send search terms to public data providers. Avoid putting personal medical details in prompts, use a dedicated Tavily key if enabling search, and pin dependency versions if reproducible installs matter.

SkillSpector

By NVIDIA

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill declares use of environment variables and includes a search component that depends on an API key and external retrieval, but it does not expose corresponding permissions or a clear trust boundary. This can cause the host system to execute a skill with undeclared network and secret access expectations, reducing operator visibility and increasing the chance of unintended data egress or policy bypass.

Unpinned Dependencies

Low

Category: Supply Chain
Content: requests>=2.31.0 langchain-tavily>=0.2.0
Confidence: 97% confidence
Finding: The dependency is specified with only a lower bound (`requests>=2.31.0`), which makes builds non-reproducible and allows future package releases to be pulled in without review. That increases supply-chain risk and can unexpectedly introduce breaking changes or newly published malicious/compromised versions into the skill.

Unpinned Dependencies

Low

Category: Supply Chain
Content: requests>=2.31.0 langchain-tavily>=0.2.0
Confidence: 96% confidence
Finding: `langchain-tavily>=0.2.0` is also unpinned, so installations may resolve to different versions over time. For an agent skill that performs external querying, this raises supply-chain and behavior-change risk because a future package update could alter network access patterns, introduce insecure defaults, or include malicious code.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.