ClawHub
Back to skill

Security audit

A Stock Quantitative Screener

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed A-share stock-screening prompt skill, but users should treat its outputs as informational analysis rather than financial advice.

Install only if you want an agent to help screen A-share stocks. Verify market data freshness independently, treat rankings and signals as educational analysis, and do not rely on this skill alone for trading decisions.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file gives specific securities screening, buy/sell signals, scoring thresholds, and risk-control rules that a user could directly act on as investment guidance, but it does not include any warning that the material is informational only or that investing carries risk. In an agent skill context, this increases the chance users treat the content as actionable financial advice, creating user-harm, compliance, and trust risks if the guidance is inaccurate, outdated, or unsuitable for the user.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad investment-analysis phrases that can match ordinary user requests and invoke this skill outside a clearly scoped A-share quantitative-screening context. That increases the chance the agent will produce specialized stock-picking behavior and recommendations when the user did not explicitly request this exact workflow, creating misrouting and inappropriate financial guidance risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Phrases like '筛选可能拉升的股票' and '识别主力资金介入' are ambiguous, promotional, and not sufficiently tied to a defined analytical scope. They may trigger on speculative or manipulative-seeming requests and steer the model toward presenting uncertain market predictions as actionable recommendations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill directs the agent to output ranked stock lists, priority tiers, and concrete investment suggestions, but it does not prominently require a disclaimer that the content is not financial advice or ask the user to assess suitability. In context, this is more dangerous because the workflow is framed as a systematic screening engine with specific data sources and risk controls, which can make outputs appear authoritative and encourage reliance on potentially flawed or stale signals.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.