Security audit

Website Audit Checklist

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward website-audit checklist with disclosed promotional links and no code, persistence, credentials, or privileged behavior.

Install this as a lightweight checklist skill. Be aware that it includes Atlas paid ZIP pack marketing links and broad discovery keywords, so users or platform maintainers may prefer narrower activation terms if auto-routing is sensitive.

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: 92% confidence
Finding: The skill includes a long list of broad search keywords and use cases such as 'website audit', 'how to audit a website', and related generic audit terms. In agent ecosystems that route or auto-activate skills by keyword matching, this can cause the skill to trigger in contexts the user did not specifically intend, increasing the chance of irrelevant behavior, prompt-surface expansion, and untrusted promotional content being injected into workflows.

Static analysis

No suspicious patterns detected.