{ "openapi": "3.0.1", "info": { "title": "Dataset Egress Firewall — Allowlist, Leak Report, Provenance", "description": "Govern what leaves your datasets: allowlist projection (unknown fields never escape), deep scrub of forbidden keys (passwords, tokens, PII) at any depth, a per-run leak report, and a tamper-evident provenance tag on every record. Deterministic, LLM-free, fail-closed.", "version": "0.1", "x-build-id": "mQwvNvXh6IP3mUdZ8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/equ1n0x~dataset-egress-firewall/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-equ1n0x-dataset-egress-firewall", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/equ1n0x~dataset-egress-firewall/runs": { "post": { "operationId": "runs-sync-equ1n0x-dataset-egress-firewall", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/equ1n0x~dataset-egress-firewall/run-sync": { "post": { "operationId": "run-sync-equ1n0x-dataset-egress-firewall", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "allowFields" ], "properties": { "allowFields": { "title": "Allowed fields (the allowlist)", "type": "array", "description": "The ONLY top-level fields that may appear in emitted records. Everything else is dropped. Projection, not redaction: absence, not exposure.", "items": { "type": "string" } }, "datasetId": { "title": "Source dataset ID", "type": "string", "description": "An Apify dataset to clean — e.g. another actor's output. Can be combined with inline Items." }, "items": { "title": "Items (inline records)", "type": "array", "description": "Records to clean, pasted inline as a JSON array of objects. Can be combined with a source dataset. The prefilled demo records carry planted secrets at several depths — run as-is to watch the firewall catch all of them and hand you the receipt." }, "forbiddenKeySubstrings": { "title": "Forbidden key substrings (the tripwire)", "type": "array", "description": "Case-insensitive substrings. Any key containing one of these — at ANY nesting depth — is scrubbed and reported. Leave empty to use the built-in default vocabulary (passwords, tokens, PII, debug/internal machinery). Over-broad on purpose.", "items": { "type": "string" } }, "allowedNestedKeys": { "title": "Allowed nested keys (optional strict mode)", "type": "array", "description": "If set, keys inside nested objects must also be on this list to survive. Leave empty to keep all nested structure except forbidden keys.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "scrub", "fail-closed" ], "type": "string", "description": "scrub: clean every record and emit the clean dataset. fail-closed: if ANY forbidden field exists in the input, abort and emit NOTHING (use this as a shipping gate).", "default": "scrub" }, "provenanceSecret": { "title": "Provenance secret (optional)", "type": "string", "description": "If set, every clean record is stamped with an HMAC provenance tag (fw1:…) derived from this secret, so consumers holding the secret can verify a record passed this firewall untampered. Without it, records carry a content-hash tag (fw0:…)." }, "stampProvenance": { "title": "Stamp provenance tags", "type": "boolean", "description": "Add a provenance tag to every emitted record.", "default": true }, "maxItems": { "title": "Max records", "minimum": 1, "type": "integer", "description": "Upper bound on records read from the source.", "default": 10000 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }