Security audit

Alphagbm Greeks

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow options-Greeks helper that discloses its external API use and does not include executable code, persistence, or hidden local access.

Before installing, understand that real option contract or portfolio-position details may be sent to AlphaGBM if you use the live API. Use mock or non-sensitive data when appropriate, keep the API key in environment variables, and avoid sharing positions you consider confidential.

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 (3)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill instructs users to configure an external-service API key and send option/position inputs to a remote base URL, but it provides no warning about credential handling, third-party transmission, or sensitivity of portfolio data. In a finance-related context, positions, strikes, expiries, and strategy structure can be commercially sensitive, so silent transmission to an external API increases privacy and operational risk.

Vague Triggers

Low

Confidence: 91% confidence
Finding: This markdown file declares invocation triggers, so vague-trigger review applies. While most examples are specific, "position Greeks" lacks scope constraints and could activate in many generic options-risk conversations without making clear when the skill should or should not run.

Vague Triggers

Low

Confidence: 88% confidence
Finding: The phrase depends on an unspecified previously defined position, but the skill description does not clearly state the activation prerequisites or exclusion conditions. That ambiguity can cause unintended invocation or user confusion about when the skill is applicable.

Static analysis

No suspicious patterns detected.