ClawHub
Back to skill

Security audit

靶点药物BD综合评估（Target-Drug BD Assessment）

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed report-generation workflow for target and drug BD assessment, with no hidden persistence, credentials, destructive actions, or unrelated data access found.

Before installing, understand that the skill is designed to produce research-heavy BD reports and may use external research tools or web supplementation when available. Generated HTML reports may be written to the session outputs area; review sources and disclaimers carefully before relying on business, patent, clinical, or strategic conclusions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
82% confidence
Finding
The spec instructs the skill to save a generated file into the session output directory without requiring explicit user consent or clear disclosure. While the path is constrained to a session-scoped location, silent file creation can surprise users, create unintended artifacts, and normalize side effects that become riskier if similar patterns are reused with broader file-write capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.