Security audit

site-architecture

Security checks for vulnerabilities and agentic risk

Overview

This skill provides website site-architecture planning guidance and does not contain hidden execution, credential handling, persistence, or destructive behavior.

Installers should expect this skill to help an agent ask planning questions, read project-level product-marketing context if available, and produce sitemap/navigation/URL recommendations. Review any local product-marketing files before use if they contain sensitive business strategy, but no hidden or high-impact behavior was found.

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 (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The manifest description says 'When the user wants to plan, map, or restructure their website's page hierarchy...' and 'Use this whenever someone is planning what pages a website should have and how they connect.' Those conditions are broad natural-language cues rather than a tightly bounded trigger specification, which increases the chance of unintended invocation during general web strategy conversations.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: This JSON eval file is a manifest-type file, so vague-trigger checks apply. The expected behavior explicitly says the skill 'Should trigger on casual phrasing,' and the paired prompt is a common conversational question about URL structure; this broadens activation beyond clearly bounded, domain-specific triggers and provides no exclusion conditions or negative examples.

Static analysis

No suspicious patterns detected.