ClawHub
Back to skill

Security audit

Wheel Strategy Options Screen (via Finch)

Security checks for vulnerabilities and agentic risk

Overview

The skill sends relevant financial inputs to a clearly named options-analysis service and requires approval before paid runs.

Finch receives the financial inputs you provide for analysis. Share only the requested details, review Finch's privacy terms and connection permissions, and explicitly approve any paid run.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends the user's financial information to Finch without an explicit privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow collects potentially sensitive financial details, including available cash, share holdings, and cost basis, then directs the assistant to submit the user's input to Finch without first obtaining informed approval for that disclosure. Identifying Finch as the service provider makes this an expected integration rather than covert exfiltration, but does not clearly establish that the user understands which financial details will leave the conversation. The trading context makes these inputs relevant and limits suspicion of malicious intent, while leaving a meaningful privacy and consent gap.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.