ClawHub
Back to skill

Security audit

Alphagbm Bps Backtest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AlphaGBM backtesting helper that sends strategy parameters to an API, with no local code execution, persistence, or hidden privilege behavior found.

Before installing, treat this as a remote financial-research integration: only use it when you intend to spend an AlphaGBM option-analysis credit and share the ticker, date range, and strategy parameters with the AlphaGBM service. It does not show local execution or persistence behavior in the inspected artifact.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
87% confidence
Finding

The trigger phrases are broad enough to match ordinary financial discussion rather than clearly delimited skill-invocation intent. That can cause unintended activation of a remote backtesting workflow, leading to unexpected API calls, compute consumption, and transmission of user-supplied strategy parameters when the user may only be asking a general question.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents a POST request to a remote API but does not warn users that their ticker, dates, and strategy parameters will be transmitted off-platform. In a finance context, those inputs can reveal trading interests or research behavior, so the missing disclosure creates a privacy and consent issue even if the payload is not highly sensitive by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.