ClawHub
Back to skill

Security audit

yumstock

Security checks for vulnerabilities and agentic risk

Overview

This is a single markdown stock-analysis skill whose web/data access is disclosed and aligned with producing current market research.

Install only if you are comfortable with the agent querying external financial and macro data sources for tickers you ask about. Treat its Buy/Hold/Sell outputs as educational analysis, not as trading instructions or professional financial advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly directs the agent to use web search, tools, or APIs to fetch live market and macro data, but it does not require disclosure or consent before initiating outbound requests. In an agent environment, this can cause unexpected network access, reveal user interest or prompts to third parties, and create privacy/compliance issues even if the retrieved data itself is non-sensitive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is primarily written in English but introduces Chinese terminology such as '量价结构确认' and later '低估型启动' and '热门行业回调' without stating that bilingual output is optional or user-selected. This can impose a locale/language expectation on users who did not opt in to Chinese labels.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.