ClawHub
Back to skill

Security audit

Alphagbm Take Profit

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malware, but it can trigger on broad investment questions and produce concrete stock sell-order suggestions without adequate user-control or financial-risk safeguards.

Review before installing if you do not want an agent to answer broad stock sell/hold questions with model-based exit recommendations. Treat outputs as scenario analysis, not personalized financial advice, and do not place generated orders without independent review of risk, taxes, liquidity, position size, and your own suitability.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes very broad investing phrases such as 'when to sell NVDA', 'exit strategy for my stock', and 'leveraged ETF hold analysis', which are likely to match ordinary user requests beyond a narrowly scoped tool invocation. That can cause the skill to activate unexpectedly and deliver prescriptive financial guidance in contexts where the user did not explicitly request this specific methodology, increasing the chance of inappropriate or overconfident advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the caller to 'Generate concrete GTC limit-sell orders at entry × 1.5 / 2.0 / 3.0' without a prominent warning that outputs are informational, model-based, and not personalized financial advice. In the context of a tool that analyzes securities and recommends exit strategies, this makes the skill more dangerous because it encourages direct trading actions from a backtested heuristic that may be unsuitable for a user's risk tolerance, taxes, liquidity, or regulatory constraints.

Content

No source excerpt is available for this finding.