ClawHub
Back to skill

Security audit

Alphagbm Buffett Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed stock-analysis skill that calls a Buffett-style scoring API for user-provided tickers, with no evidence of hidden execution, credential access, persistence, or destructive behavior.

Before installing, be aware that it may spend one stock-analysis credit when invoked and may return opinionated investment labels such as HOLDABLE, WATCHABLE, or AVOID. Treat those as research output, not trading advice, and use explicit Buffett-related prompts if you want to avoid accidental activation.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad natural-language phrases such as 'fair price vs bonds' and 'long-term hold analysis' that can match ordinary investing conversation outside a clear Buffett-analysis intent. This can cause unintended skill activation, leading to incorrect routing, surprise API calls, or disclosure of this skill's opinionated financial output when the user did not explicitly request it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documented output schema requires both Chinese and English fields such as verdict_zh, verdict_en, reasons_zh, and reasons_en, indicating a fixed locale behavior rather than a user-selected language preference. This can violate language-choice policy when the skill imposes specific languages without offering opt-in or configuration.

Content

No source excerpt is available for this finding.