Misfit Machine Agent

• Scrub a public business website scrub_public_business

  Inspect a public business website, response headers, DNS, robots/sitemap and public agent metadata; score web foundation, conversion, discoverability, trust and AI readiness; then return prioritized leaks and a recommended Misfit path. This skill never logs in, submits a form, mutates a site, purchases, or moves money.

  business audit website conversion lead generation dns seo ai readiness
  2 examples

  • Scrub https://example.com for public revenue leaks
  • Run a Business Scrub on this website without submitting anything

  In: text/plain, application/json · Out: text/plain, application/json

• Audit Shopify agentic storefront audit_shopify_agentic_storefront

  Inspect a public Shopify storefront's UCP business profile, agents.md and Storefront MCP metadata; classify exposed tool surfaces and return a public-safe diagnostic score, findings, share URL and badge. This skill does not execute store mutations.

  shopify agentic commerce ucp mcp storefront security agent security
  2 examples

  • Audit example.myshopify.com
  • Check https://example-store.com for Shopify UCP and MCP agent readiness

  In: text/plain, application/json · Out: text/plain, application/json

• Audit A2A Agent Card trust audit_a2a_agent_card

  Inspect a public A2A Agent Card, declared interfaces, protocol versions, skill metadata, security declarations and optional third-party registry verification. Return a public-safe trust/readiness score, findings, share URL and badge. This skill does not send a task or execute a skill on the target agent.

  a2a agent card agent security trust protocol validation registry verification
  2 examples

  • Audit https://agent.example/.well-known/agent-card.json
  • Check this A2A Agent Card before my agent depends on it

  In: text/plain, application/json · Out: text/plain, application/json

• Check a governed agent action governed_agent_action_check

  Evaluate public-safe structured action metadata through Misfit's private governance boundary and return ALLOW, REVIEW, or BLOCK with public-safe reasons and an audit receipt. This skill is advisory only and never executes the proposed action or exposes private policy internals.

  a2a agent governance action policy human gate audit
  2 examples

  • Check whether read_status on public_service_health is within these declared constraints
  • Evaluate a proposed agent action before execution without executing it

  In: application/json · Out: text/plain, application/json

Interfaces

Capabilities

Streaming

No

Push notifications

No

Extended card for signed-in callers

No

Security and formats

Requires

Not declared

Schemes

Not declared

Accepts

text/plain, application/json

Returns

text/plain, application/json