ClawHub
Back to skill

Security audit

Argus Edge — Prediction Market Betting Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for prediction-market betting analysis; it has financial-risky guidance but no hidden code, persistence, credential use, or install-time behavior.

Install only if you want an agent to provide prediction-market betting analysis. Treat its win-rate and edge claims as unverified, require explicit confirmation before any live market scan or stake-sizing recommendation, and do not let an agent place bets or use account credentials based solely on this skill.

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
  • 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
92% confidence
Finding
The manifest description uses broad, generic invocation language such as 'Use for prediction market betting' and related strategy terms, which can cause the skill to be selected in overly broad contexts without clear scope restrictions. In an agentic system, this increases the chance of inappropriate routing to a high-risk financial decision skill, potentially leading to unvetted betting or market-making guidance being surfaced when the user intent is only loosely related.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The usage examples are phrased as open-ended activation commands like 'find the best Polymarket bet right now' and 'full market scan with Kelly sizing' without constraints, safety boundaries, or clarifying requirements. That makes the skill easier to invoke for autonomous or overly broad financial recommendation behavior, especially because the skill explicitly performs edge detection and bet sizing for real-money markets.

Static analysis

No suspicious patterns detected.