TaskHawk Systems · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Taskhawktech Com Shield API

3 actions 3 updates phrasing extends openapi/taskhawktech-com-shield-api-openapi.yml

Generated by API Evangelist Written by API Evangelist tooling for TaskHawk Systems's API. It is a proposal applied on top of the contract, not a document TaskHawk Systems publishes.

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 3

$.info

$.paths['/shield/scan'].post

$.paths['/shield/scan-free'].post

OpenAPI Overlay

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Taskhawktech Com Shield API
  version: 1.0.0
extends: openapi/taskhawktech-com-shield-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 2
- target: $.paths['/shield/scan'].post
  update:
    x-apievangelist-phrasing:
      intent: Scan a prompt for injection attacks (paid)
      effect: read
      questions:
      - How do I check a prompt for injection attacks with my API key?
      - What does a paid prompt injection scan cost per call?
      - Can I pass context about where a prompt came from when scanning it with my key?
      instructions:
      - text: Scan {prompt} for prompt injection using my API key.
        slots:
          prompt: requestBody.prompt
      - text: Run a paid injection scan on {prompt} for agent {agent_id}, noting the source as {context}.
        slots:
          prompt: requestBody.prompt
          agent_id: requestBody.agent_id
          context: requestBody.context
      method: generated
      generated: '2026-10-01'
- target: $.paths['/shield/scan-free'].post
  update:
    x-apievangelist-phrasing:
      intent: Scan a prompt for injection attacks for free
      effect: read
      questions:
      - Is there a free prompt injection scan I can use without signing up?
      - How many free injection scans per day do I get from one IP?
      instructions:
      - text: Use the free no-auth scanner to check {prompt} for injection.
        slots:
          prompt: requestBody.prompt
      - text: Do a free daily-quota injection scan of {prompt} with source context {context}.
        slots:
          prompt: requestBody.prompt
          context: requestBody.context
      method: generated
      generated: '2026-10-01'