ClawHub
Back to skill

Security audit

simmer-wallet-setup

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed wallet-setup guide for real-money trading agents, with high-value keys and automated exits called out rather than hidden.

Install only if you intend this agent to control a funded trading wallet. Prefer OWS or another scoped key store over a raw private-key environment variable, review the Simmer dashboard auto risk monitor settings before polling get_briefing, and understand that approvals and cached trading credentials can let the agent place or exit real-money positions.

SkillSpector

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Risk monitor

The auto risk monitor (stop-loss, take-profit) is configured at simmer.markets/dashboard → Settings → Auto Risk Monitor. The SDK auto-executes pending exits each `get_briefing()` cycle. The agent must be running.

## Troubleshooting
Confidence
83% confidence
Finding
The skill states that the SDK auto-executes pending exits on each `get_briefing()` cycle, meaning a seemingly informational polling call can trigger real-money trading actions. This coupling of read-like operations with autonomous execution increases the chance of unintended trades, makes behavior less auditable, and can be dangerous if an agent or integration invokes `get_briefing()` more broadly than intended.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.