Security audit

Adversarial Design Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed adversarial design-review workflow that uses parallel review agents, with no hidden install code, persistence, exfiltration, or unrelated authority.

Install this if you want a structured multi-agent review for risky systems designs. Be aware that invoking it may cause several agents to inspect the repository files you name or the surrounding code needed to evaluate the design, so use it only in workspaces where that review is appropriate.

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 (3)

Ae1

High

Category: analysis-evasion
Content: [`resources/attack-workflow.template.js`](resources/attack-workflow.template.js).
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: [`resources/attack-workflow.template.js`](resources/attack-workflow.template.js).
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The manifest description lists generic triggers such as "design review", "before I build", and "review before implementing" without clear constraints on scope. These phrases are broad enough to match ordinary conversation about planning work, which could cause unintended invocation of the skill.

Static analysis

No suspicious patterns detected.