ClawHub
Back to skill

Security audit

investoday-stock-valuation-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent stock valuation helper that queries public A-share market data and does not show hidden execution, persistence, or private-data handling.

Install this if you want valuation-style analysis for A-share stocks and are comfortable with the dependent finance-data skill querying public market APIs for the stock you mention. Treat outputs as informational, not investment advice, and be aware that broad phrases like 'expensive' or 'worth watching' may route some ambiguous finance questions into this valuation workflow.

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
92% confidence
Finding

The trigger phrases include broad natural-language terms such as '贵不贵' and '便宜不便宜', which can appear in many general finance conversations and may cause the skill to activate when the user did not explicitly request valuation analysis. Unintended invocation can lead to unnecessary external data access and context switching, increasing the chance of incorrect routing or disclosure of user intent to dependent tools.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger scenarios are broad and do not define exclusion conditions, so ordinary market commentary like '值不值得继续看' or '有没有修复空间' may invoke this skill even when the user wants technical analysis, news interpretation, or general advice. In an agent environment, ambiguous routing increases the risk of the wrong skill calling external APIs and producing mismatched outputs that the user did not request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.