ClawHub
Back to skill

Security audit

Social Arbitrage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed financial research workflow that uses public or user-authorized sources and repeatedly limits itself away from trade execution, brokerage access, MNPI, manipulation, and private data exposure.

Before installing, treat outputs as research leads, not investment advice. Only authorize signed-in social or browser access when you are comfortable with the agent inspecting that account-gated content, and do not provide brokerage credentials, funds access, or material nonpublic information.

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

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
55% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/report-template.md (reported line 161)May include surrounding context.

md
## Why the set is empty

State which gates most often failed and whether access gaps affected the result. Do not apologize for an empty set.

## Coverage