ClawHub
Back to skill

Security audit

Daily Options Plays — Top 2 Picks

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped paper-trading options watchlist guide, with no code, persistence, credential access, or hidden behavior found.

Use this as an educational market-planning aid, not as automatic trading advice. Confirm any market data, options chains, liquidity, and risk levels independently before acting, and avoid giving it brokerage credentials or live execution authority unless a separate, trusted tool clearly handles that with your consent.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
6. Default to paper-trade-first language unless the user explicitly asks for live execution framing.
7. Re-check the watchlist roughly once per hour, not every few minutes, unless the user requests a live drill-down.

## Output Rules

- Keep the writeup concise and easy to scan.
- Prefer liquid large-cap names and obvious levels over exotic setups.

Static analysis

No suspicious patterns detected.