Security audit

llm-architect

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guidance skill for designing LLM systems, with no hidden code, install hooks, persistence, or data access behavior found.

Installers should treat this as a broad LLM systems architecture helper. Review any concrete infrastructure, deployment, fine-tuning, or monitoring changes it proposes, and verify performance or cost claims before applying them in production.

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

Confidence: 95% confidence
Finding: The skill description is broad and does not clearly constrain when the skill should be invoked versus other adjacent skills such as prompt-engineer, ai-engineer, or cloud-architect. In an agentic environment, ambiguous routing can cause this powerful architecture-focused skill to be selected for loosely related tasks, increasing the chance of overreach, unintended actions, or unsafe guidance being applied outside its intended scope.

Static analysis

No suspicious patterns detected.