Back to skill

Security audit

a-stock-profit-taking

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only stock profit-taking strategy skill with no code execution, persistence, credential use, or account-control behavior.

Install only if you want generic A-share profit-taking guidance. Treat its sell percentages as educational strategy, not personalized financial advice, and do not connect it to automatic trading without separate safeguards and explicit confirmation steps.

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
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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are broad enough to match ordinary investing chat such as whether to sell, how to take profits, or whether to keep holding. In an agent system, this can cause unintended invocation outside a clearly scoped context, leading the skill to influence financial decisions when the user may only be asking a general question or seeking analysis rather than a concrete strategy.

Static analysis

No suspicious patterns detected.