ClawHub
Back to skill

Security audit

Ai Ethnobotany

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be informational content, with a safety-warning gap around psychoactive plant discussion but no evidence of hidden code, persistence, credential access, or unsafe automation.

Install only if you want educational ethnobotanical content, and treat any psychoactive-plant discussion cautiously. Do not rely on it for consumption, dosing, extraction, cultivation, self-treatment, or legal decisions; consult qualified medical or legal professionals where relevant.

SkillSpector

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

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly describes several psychoactive plants and their active compounds, effects, and cultural/legal context without any accompanying safety, medical, or legal warning. In an agent setting, this can normalize or facilitate unsafe guidance about substances with intoxication, toxicity, dependency, psychiatric, and jurisdiction-specific legal risks, especially if the model later expands on use, sourcing, or preparation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.