ClawHub
Back to skill

Security audit

dalio-macro-analysis

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only macro analysis skill with disclosed finance-oriented guidance and no code, persistence, credential access, or data exfiltration behavior.

Review the broad trigger terms and the Chinese-language workflow before installing. Treat its portfolio allocations and macro views as educational framework output, not personalized financial advice, and verify market data independently.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list contains broad generic terms such as macroeconomics, Fed, principles, and geopolitical risk that are likely to match many ordinary finance conversations. This can cause the skill to activate outside the user's intent, injecting investment-allocation guidance and opinionated market views into unrelated discussions, which is a scope-control and prompt-selection vulnerability rather than a code-execution issue.

Natural-Language Policy Violations

Medium
Confidence
76% confidence
Finding
Most of the skill is written only in Chinese and the examples, workflow, and outputs assume Chinese-language interaction, with no explicit language negotiation or supported-locale statement. In practice this can cause misinterpretation of user requests, reduce transparency for non-Chinese-speaking reviewers, and increase the chance that users receive output they cannot validate, especially in a finance-oriented skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.