ClawHub
Back to skill

Security audit

A Stock Trading Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed A-share stock-analysis skill with financial-advice and local watchlist caveats, but no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you want an A-share-focused assistant. Treat its trading suggestions as informational, confirm market scope when asking ambiguous questions, and be aware that price alerts may be stored locally in a watchlist file if you ask it to monitor targets.

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
91% confidence
Finding
The activation text is broad enough to trigger on general investing or trading discussion, not just narrow A-share data lookups. That can cause the assistant to enter a high-risk finance workflow unexpectedly, leading to unsolicited trading guidance, inappropriate tool use, or overconfident financial advice in contexts where the user did not clearly request this specialized skill.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill hardcodes a single market and locale behavior and states it only serves mainland China A-shares while automatically ignoring other markets, without checking the user's language or market preference. In ambiguous conversations, this can mis-handle user intent, suppress relevant alternatives, and produce incorrect or incomplete financial guidance if the user meant Hong Kong, U.S., or multilingual support.

Static analysis

No suspicious patterns detected.