ClawHub
Back to skill

Security audit

A-Stock Sentimental Cycle

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, Markdown-only A-share market sentiment analysis guide that uses expected financial data sources and does not show hidden execution, persistence, or exfiltration behavior.

Install only if you want the agent to perform A-share sentiment-cycle analysis using market-data tools or the configured Eastmoney API key. Treat the generated position guidance as trading reference, not investment advice, and confirm before relying on external API calls if cost or data-sharing matters to you.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to match many generic market-analysis requests, increasing the chance this skill is invoked when the user did not specifically ask for sentiment-cycle analysis. In a multi-skill agent, unintended invocation can cause scope overreach, unnecessary external data access, and advice framed more narrowly than the user intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The report template requires every analysis to be output in a specific Chinese structure ('每次研判输出严格按以下格式') and all examples/instructions are Chinese-only. There is no indication that the user may choose another language, which is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.