A11y Audit Migrated
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill shows no executable code or required credentials, but its examples rely on other local skills/subagents and mention short-term caching.
This skill appears low risk by itself because it contains only documentation and no executable code. Before using the example integrations, make sure the referenced local skills and any caching behavior are understood and trusted, especially for private websites or internal accessibility audits.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If a user follows the examples, the agent may load other local skills whose behavior was not reviewed here.
The documentation references other local skill modules that are not included in this artifact set. This is not automatic execution, but following the examples would depend on separately reviewed code.
const { OptimizedSubagent } = require('~/.opencode/skills/subagente-optimizado'); ... const search = require('~/.opencode/skills/exa-search');Review and trust the referenced local skills before using these examples, especially the subagent and web-search integrations.
Using the advanced example could pass task context or tool access to a separate subagent implementation.
The advanced example delegates context and tools to another agent-like component, but the artifact does not describe that component's data boundaries or permissions.
const agent = new OptimizedSubagent({ ... context: { userGoal: 'Objective' } }); ... await agent.execute(async ({ context, tools }) => {Only use the subagent pattern with trusted, reviewed subagents and avoid passing sensitive context unless its handling is clear.
Accessibility audit results or context might persist briefly if a referenced implementation performs the claimed caching.
The skill claims that results may be cached for one hour. No implementation is present, and the TTL is bounded, but users should be aware that audit outputs could be reused if this behavior exists elsewhere.
Result caching (TTL: 1h)
Confirm where cached results are stored before auditing private pages, unreleased products, or sensitive internal content.