ClawHub

Codex Agentic Gateway

Security checks across malware telemetry and agentic risk

Overview

The skill appears focused on Tempo wallet payments, but its rules can trigger wallet login and paid USDC-backed requests without clearly requiring explicit user confirmation first.

Review this skill before installing if the wallet has funds. Use it only when you want the agent to make paid Tempo requests, keep wallet balances limited, and require the agent to ask before logging in, signing payment credentials, or retrying a paid request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The rule instructs the agent to automatically run `tempo wallet login` and retry when authentication fails, but provides no requirement to warn the user or obtain confirmation first. Because login opens a passkey-based authentication flow tied to a funded wallet, this can trigger sensitive auth/payment-related actions unexpectedly and may cause the user to authorize spending-capable sessions without clear intent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The paid request workflow says `tempo request` automatically handles the 402 challenge, signs a Tempo transaction, and retries the request, but it does not require an explicit warning that this may initiate blockchain-backed payment activity from the user's funded wallet. In this skill context, the omission is more dangerous because the tool is specifically designed to spend funds per query, so silent or poorly disclosed execution can lead to unintended monetary loss.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal