ClawHub
Back to skill

Security audit

Stock Research System

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language stock research workflow skill with no embedded executable payload, persistence, credential handling, or hidden behavior found.

Install this if you want a Chinese-language equity research workflow that can call financial data and search integrations. Review outputs carefully before making investment decisions, and be aware that broad finance prompts may route into this structured report process.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases in metadata are broad generic finance terms like '股票研究', '深度研究', and 'DCF估值', which can match ordinary user requests and cause the skill to activate unexpectedly. Over-broad activation expands the skill's execution surface, potentially routing unrelated conversations into this workflow, invoking external data access paths, and overriding more appropriate handling.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The manifest description is entirely in Chinese and presents the skill as a general-purpose stock research system, but it does not state that use is limited to Chinese-speaking users or offer a language choice. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The dedicated trigger section repeats ambiguous activation phrases without scope boundaries, increasing the chance of accidental invocation from routine finance questions. Because this skill can initiate multi-step analysis and external data retrieval, accidental activation can lead to unnecessary tool use, unintended data access, and user confusion about why the system switched into a structured research mode.

Static analysis

No suspicious patterns detected.