Security audit

ai-engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple AI engineering guidance skill with broad topic coverage but no hidden execution, persistence, or sensitive access.

Before installing, expect this skill to be used for a wide range of AI and ML engineering questions. It does not itself run code or access data, but users should still review generated AI/ML implementation advice for privacy, security, and compliance needs in their specific project.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill’s activation criteria are overly broad, covering generic AI and ML topics without clear scope boundaries or exclusions. This can cause the orchestrator to invoke the skill in situations where specialized security, privacy, or domain-specific safeguards are needed, increasing the risk of inappropriate guidance or overreach.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.