ClawHub
Back to skill

Security audit

Investment Research Analyst

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed stock-research report generator with expected market-data, web-search, dashboard, and deployment behavior, but users should treat its financial output cautiously.

Install only if you want AI-assisted investment research. Verify financial data independently, do not treat the report as investment advice, and review any generated dashboard before deployment because deployed reports may expose analysis or portfolio context.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes very broad phrases such as 'company research' and 'stock analysis', which can cause the skill to activate in contexts the user did not clearly intend. In an agent setting, over-broad invocation can route unrelated requests into a finance workflow, increasing the chance of unwanted tool use, misleading outputs, or accidental generation of investment-oriented content.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill states behavior in Chinese without indicating adaptation to the user's preferred language, which can override user expectations and reduce transparency. While not a direct security flaw, forced language behavior can degrade usability, obscure important disclaimers or risk information, and contribute to unsafe misunderstandings in a financial-analysis context.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list uses broad, generic phrases such as company research, stock analysis, and investment research, which are likely to overlap with many ordinary user requests. This can cause the skill to activate unexpectedly and steer users into financial-analysis behavior without clear intent, increasing the risk of inappropriate invocation in sensitive financial contexts.

Static analysis

No suspicious patterns detected.