ClawHub

Kamino Positions Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says, but users should review the external Node project before running it.

Install only if you are comfortable running the linked Node project. Review the repository and dependencies first, prefer a pinned commit or release, keep wallets.json limited to public wallet addresses, use dedicated RPC or Telegram credentials if enabled, and do not provide private keys or seed phrases.

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 skill description and metadata use broad trigger language like 'Solana lending risk' and 'DeFi fund health,' which can cause the agent to invoke this skill for loosely related finance conversations rather than only for explicit Kamino position monitoring. This is primarily a scope-control issue: it can lead to unnecessary execution, exposure of wallet-related workflows, or confusing responses, though it does not itself introduce direct code execution or privilege escalation.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The 'When to Use' section contains ambiguous activation conditions like 'Solana lending' and 'DeFi monitoring' without clear boundaries, making overbroad routing more likely. In context, this skill handles wallet-specific monitoring and may prompt use of local files, RPC access, and reporting flows, so accidental invocation can cause unnecessary handling of sensitive financial context or produce misleading operational recommendations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal