Security audit

Agent Decision Engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local JavaScript decision-making library and does not show hidden data access, persistence, network activity, or unsafe authority.

Safe to install for local decision-model experiments, but users should review the API mismatch around the missing DecisionEngine export and the Q-learning reset behavior if they rely on custom epsilon settings.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The module presents itself as a customizable Q-learning implementation, and the constructor allows callers to configure epsilon-related parameters. However, reset() unconditionally sets epsilon to 0.1 rather than restoring the originally configured value, which contradicts the documented customizable behavior and changes runtime intent after reset.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.