Back to skill

Security audit

stock-research-engine

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown stock-research skill whose network/data use is aligned with financial analysis, with no code execution, persistence, credential access, or destructive behavior found.

Install this if you want a Chinese-language stock research workflow that relies on current public financial data searches. Be aware it may trigger on broad company or ticker questions, and its outputs can influence investment thinking, so users should verify figures and treat conclusions as analysis rather than 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and content strongly prescribe Chinese output without any opt-in or user-language negotiation. This can override user preference, reduce usability, and in some environments create policy/compliance issues if the user expects another language or accessibility-compatible output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger scope is very broad: it activates on generic phrases like '分析一下XXX', '这个公司怎么样', and stock tickers, which can capture many ordinary conversational requests beyond the user explicitly asking for this specific workflow. Over-broad activation can cause unintended tool/skill routing, leading to irrelevant processing, excessive data retrieval, or bypass of more appropriate skills and user intent boundaries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown skill file presents all instructions and outputs in Chinese without indicating that the user can choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.