Back to skill

Security audit

Stock Analyzer | 股票深度分析

Security checks for vulnerabilities and agentic risk

Overview

This stock-analysis skill is coherent and disclosed, with expected web data lookup but no hidden persistence, credential access, or destructive behavior.

Before installing, understand that the skill may contact third-party financial sites using stock tickers or company names you provide, and its investment conclusions should be treated as research assistance, not professional financial advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to match ordinary investing conversations, which can cause the skill to activate in situations the user did not clearly intend. In a skill that may perform detailed analysis and invoke external data-gathering tools, ambiguous activation increases the risk of unexpected tool use, misleading outputs, or overreach into regulated financial-advice-like behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly instructs the agent to use exec+curl, web_fetch, and browser access to third-party financial sites, but it does not clearly disclose outbound network activity or obtain user confirmation. This can lead to unexpected transmission of user-provided stock interests or query contents to external services and creates unnecessary exposure to untrusted remote content.

Content

No source excerpt is available for this finding.