ClawHub
Back to skill

Security audit

tokenomics-decoder

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed crypto due-diligence report generator, but it contradicts its own educational-only limits by requiring direct hold/dump/daytrade-style guidance.

Review carefully before installing. The skill does not appear to trade, steal data, persist state, or run code, but it can produce direct-sounding crypto action guidance despite its disclaimers. Treat outputs as unverified research notes, not investment advice, and do not provide API keys unless needed for rate limits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The skill presents itself as an educational due-diligence tool but its required output includes action-oriented trading guidance such as whether to daytrade safely or whether an airdrop farmer should hold or dump. That contradiction can steer users toward de facto financial recommendations while disclaiming responsibility, increasing the risk of unsafe or non-compliant advice.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The skill explicitly states it will never use buy/sell/hold as recommendations, yet the mandated cheat-sheet output includes exactly those terms. This inconsistency weakens safety controls and makes it likely the agent will produce prohibited investment-style guidance despite the stated restriction.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger keywords are broad phrases like 'crypto analysis,' 'contract audit,' and 'FDV,' which can match ordinary discussion and cause the skill to activate outside its intended narrow use case. Over-broad activation is dangerous here because the skill generates detailed token risk reports that can drift into financial guidance even when the user did not explicitly request this workflow.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The invocation guidance covers broad prompts such as 'is this token safe to buy?' and general comparison requests without clear boundaries from ordinary investing or crypto Q&A. In context, that makes the skill more dangerous because it can transform general market conversation into structured, authoritative-seeming investment guidance.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.