ClawHub
Back to skill

Security audit

ta-philosophy

Security checks across malware telemetry and agentic risk

Overview

This is a static educational skill about technical-analysis philosophy and does not request sensitive access or perform actions.

Installers should treat this as an educational trading-analysis skill, not financial advice. It appears safe from an agent-permission perspective, but users should remember it presents technical analysis as an empirical worldview and should not use it alone for real trading decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The skill metadata and content are written in a fixed Chinese-first bilingual form, but there is no natural-language instruction indicating that the user's preferred language should be respected or that language choice is optional. Under the policy, forcing a specific language or locale without opt-in can be a violation when no user choice is offered.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.