Back to skill

Security audit

Accessibility Review

Security checks for vulnerabilities and agentic risk

Overview

This accessibility audit skill is a coherent markdown-only helper, with a minor caution that it can use connected design or project-tracker tools if the user has them enabled.

Install this if you want an accessibility-review prompt for designs or pages. Before allowing connector actions, confirm which design and project-tracker tools are connected and ask the agent to get confirmation before creating tickets.

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
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 trigger phrase "is this accessible?" is broad natural language that could match ordinary conversation and unintentionally invoke the skill outside a clear command context. In an agent environment, overly permissive triggers can cause unintended tool activation, unnecessary connector access, or misrouting of user intent even though the skill itself is not inherently dangerous.

Static analysis

No suspicious patterns detected.