ClawHub
Back to skill

Security audit

A股市场全面复盘，整合指数表现、板块热力图、涨跌停、风格轮动、市场温度分析。触发词：市场复盘、今天市场怎么样、市场分析、每日复盘、市场概览。适用场景：对当日A股市场进行全面复盘、生成综合市场分析报告。不适用场景：个股深度分析、单一指标分析、债券/基金分析。

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A-share market recap helper that uses an external market-data CLI and has manageable credential and trigger-scope cautions.

Install this only if you trust DAXIAPI and are comfortable running its npm CLI. Configure the API token carefully, preferably outside chat transcripts, and consider reviewing or pinning the CLI instead of relying on @latest. Use the skill for explicit A-share market recap/report requests, not generic financial questions or investment decisions.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
90% confidence
Finding
The skill’s stated purpose is market review/report generation, but it also instructs the agent to check, set, and persist an API token on the host via CLI config or environment variables. This expands the skill from analysis into credential management, creating unnecessary secret-handling risk and potential persistence of sensitive tokens on the local system.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill includes credential-management behavior that is not necessary for its declared function of producing market review reports. Asking the agent to retrieve, set, and validate tokens increases the attack surface for secret exposure, accidental logging, misuse, or persistence beyond the user’s intent.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The trigger phrases include broad everyday expressions such as '市场分析' and '市场概览', which can cause the skill to activate in contexts broader than intended. Because this skill can initiate CLI-based data access and token-related setup, overbroad triggering increases the chance of unintended execution and unnecessary exposure to secret-handling or external-command behavior.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The detailed trigger list still contains ambiguous phrases that do not sufficiently constrain when the skill should run. In a skill that performs external CLI calls and may enter credential setup flows, weak activation boundaries materially increase the risk of accidental invocation and unintended side effects.

Static analysis

No suspicious patterns detected.