ClawHub
Back to skill

Security audit

Tcm Biomedical Research Strategist

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only research planning aid for TCM/herbal biomedical studies and does not request system access, credentials, persistence, or account control.

Install only if you want structured computational TCM/herbal mechanism study plans. Treat outputs as research-planning support, independently verify biomedical sources and methods, and do not use it for clinical decisions, dosing, patient care, or regulatory submissions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description and trigger language are broad enough to match many generic bioinformatics or pharmacology planning requests, which can cause the agent to invoke this specialized skill when a narrower or different capability would be more appropriate. This creates a scope-confusion risk: users may receive over-specialized biomedical study plans in contexts that do not actually call for TCM/network-pharmacology workflows, increasing the chance of misleading or misaligned outputs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.