verify_repair
Rescan a public page scope and verify selected baseline fingerprints. Non-default states require a visible readySelector witness.
This record as markdown: /tools/a11y-agent-skills/verify-repair.md
What verify_repair does on A11y Agent Skills
AI agents invoke verify_repair to trigger actions in A11y Agent Skills. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why verify_repair is rated High
Triggers a browser rescan/execution against a page to verify accessibility fingerprints.
From the tool's definition Rescan a public page scope and verify selected baseline fingerprints
Attacks that exploit this kind of access
The rule that runs verify_repair safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A11y Agent Skills, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For verify_repair, this is the rule to start with:
verify_repair stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A11y Agent Skills, apply this rule, and every verify_repair call is checked against it from then on.
Questions about verify_repair
Rescan a public page scope and verify selected baseline fingerprints. Non-default states require a visible readySelector witness. It is categorised as a Execute tool in the A11y Agent Skills MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the A11y Agent Skills MCP server in PolicyLayer and add a rule for verify_repair: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches A11y Agent Skills. Nothing to install.
verify_repair is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the verify_repair rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for verify_repair. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
verify_repair is provided by the A11y Agent Skills MCP server (smukh/a11y-agent-skills). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A11y Agent Skills, and thousands of servers like it.
Across the catalogue