ClawHub
Back to skill

Security audit

Alphagbm Duan Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed finance-analysis prompt for Duan-style options-selling scenarios, with no bundled code, persistence, credential access, or hidden behavior found.

Install this only if you want Duan-style options-selling analysis. Treat outputs as educational decision support, not personalized financial advice, and be aware that some broad market prompts may receive options-specific framing.

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
92% confidence
Finding

The trigger list contains broad investing phrases such as "seller strategy MSFT," "premium collection setup," and especially "nationalist seller playbook," which can cause the skill to activate for ordinary market questions that did not explicitly request this niche framework. That increases the chance of misrouting users into a prescriptive options-selling workflow, which is risky in a finance context because it may steer users toward complex derivatives advice without clear intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states it provides Chinese-native copy tailored to a specific investor community without explicitly offering user language preference or a neutral default. In isolation this is not a code-execution issue, but it can cause confusing or mismatched outputs and may reinforce culturally targeted persuasive framing in a financial decision-support context.

Content

No source excerpt is available for this finding.