Back to skill

Security audit

generic-drug-scout

Security checks across malware telemetry and agentic risk

Overview

This skill mostly matches its report-generation purpose, but it directly reads the user's Codex MCP configuration to call PatSnap services, which deserves review before installation.

Review before installing. Use it only if you are comfortable with the skill reading your Codex MCP configuration and calling the configured PatSnap/Zhihuiya MCP endpoints. Avoid using --overwrite on important directories, and prefer a workspace/output folder dedicated to this report workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to perform file reads/writes, launch local processes, and rely on network-backed MCP services, but it declares no corresponding permissions. This creates a capability/expectation mismatch that can lead to overbroad execution in environments where users or reviewers are not clearly informed of the skill’s access needs.

Agent Config Directory Access

High
Category
Agent Snooping
Content
- `server.py`:本地 HTTP 服务和由 MCP 支撑的 `/api/search` 端点。
- `assets/`:页面使用的本地图片。

后端期望 `~/.codex/config.toml` 中存在以下 MCP 服务名:

- `zhihuiya_logic_096456`:用于医药情报。
- `zhihuiya_logic_2b0355`:用于 PatSnap 专利检索/获取。
Confidence
92% confidence
Finding
~/.codex/config.toml

Agent Config Directory Access

High
Category
Agent Snooping
Content
更新 `server.py` 时:

- 不要在平台文件中嵌入 API key。
- 从 `~/.codex/config.toml` 读取 MCP URL。
- 除日期窗口外,保持 V1 查询参数固定为小分子 + CN + 晶型专利。
- 保留独立的 `rows` 和 `not_promoted` 输出,使 UI 能区分主表候选和排除记录。
- `rows` 是经过药物证据验证后进入主表的候选。
Confidence
93% confidence
Finding
~/.codex/config.toml

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/create_seeded_screening_platform.py:25