{ "openapi": "3.0.1", "info": { "title": "LLM Data Guard: PII & Secret Redactor", "description": "Detect and redact PII (emails, phones, SSNs, Luhn-checked cards, IBANs, IPs, optional names/addresses) and secrets (API keys, tokens, private keys, high-entropy strings) in text, HTML or PDF before it reaches an LLM. Placeholder, mask or hash redaction with reversible map. No data retention.", "version": "0.1", "x-build-id": "m6WgQ5rWwfmnJOpyh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fairquery~llm-data-guard-pii-secrets/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fairquery-llm-data-guard-pii-secrets", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fairquery~llm-data-guard-pii-secrets/runs": { "post": { "operationId": "runs-sync-fairquery-llm-data-guard-pii-secrets", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fairquery~llm-data-guard-pii-secrets/run-sync": { "post": { "operationId": "run-sync-fairquery-llm-data-guard-pii-secrets", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "texts": { "title": "Texts", "type": "array", "description": "Each entry is one document (prompt, chat message, ticket, log line, file content).", "items": { "type": "string" } }, "documents": { "title": "Documents with IDs", "type": "array", "description": "Optional: [{\"id\": \"ticket-42\", \"text\": \"...\"}]. The id is echoed in the output row.", "default": [] }, "documentUrls": { "title": "Document URLs", "type": "array", "description": "Optional: public URLs of text, Markdown, JSON, CSV, HTML or PDF files (max 10 MB each).", "default": [], "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "detect", "redact", "restore" ], "type": "string", "description": "detect = report findings only; redact = also return redacted text; restore = put original values back into LLM output using a placeholder map.", "default": "redact" }, "redactionStyle": { "title": "Redaction style", "enum": [ "placeholder", "mask", "hash" ], "type": "string", "description": "placeholder = [EMAIL_1] (reversible with the map); mask = j***@a***.com / **** 1111; hash = [EMAIL:sha256 prefix] (stable for the same salt).", "default": "placeholder" }, "returnPlaceholderMap": { "title": "Return placeholder map", "type": "boolean", "description": "Include {\"[EMAIL_1]\": \"jane@acme.com\"} in each row so you can restore values after the LLM answers. The map contains the original sensitive values: only enable it if you will delete the dataset after use.", "default": false }, "consistentPlaceholders": { "title": "Consistent placeholders across documents", "type": "boolean", "description": "Same value gets the same placeholder in every document of the run.", "default": true }, "placeholderMap": { "title": "Placeholder map (restore mode)", "type": "object", "description": "Map returned by a previous redact run; used only in restore mode.", "default": {} }, "hashSalt": { "title": "Hash salt", "type": "string", "description": "Optional salt for hash style. Leave empty for a random per-run salt (hashes then cannot be linked across runs)." }, "detectPii": { "title": "Detect PII", "type": "boolean", "description": "Emails, phones, US SSNs, credit cards (Luhn), IBANs (mod-97), UK NI numbers, IPv4/IPv6.", "default": true }, "detectSecrets": { "title": "Detect secrets", "type": "boolean", "description": "Gitleaks-style rules: AWS, GitHub, GitLab, Slack, Stripe, Google, OpenAI, Anthropic, Hugging Face, npm, SendGrid, Twilio, Azure keys, JWTs, private keys, URL credentials, key=value assignments with an entropy check.", "default": true }, "detectNames": { "title": "Detect person names (NER)", "type": "boolean", "description": "Open-source NER (compromise, English). Lower precision; adds a little CPU time.", "default": false }, "detectAddresses": { "title": "Detect street addresses & places", "type": "boolean", "description": "Street-address pattern (English formats) plus NER place names.", "default": false }, "entropyScan": { "title": "Flag any high-entropy string", "type": "boolean", "description": "Also flag unlabeled random-looking tokens (20+ chars). Catches unknown key formats; may flag hashes and IDs.", "default": false }, "minEntropy": { "title": "Minimum entropy (bits/char)", "minimum": 2, "maximum": 6, "type": "number", "description": "Threshold for generic key=value secrets and the entropy scan.", "default": 3.5 }, "defaultPhoneRegion": { "title": "Default phone region", "type": "string", "description": "ISO country code used for phone numbers written without +country prefix.", "default": "US" }, "entityTypes": { "title": "Only these types", "type": "array", "description": "Optional filter, e.g. EMAIL, PHONE, CREDIT_CARD, AWS_ACCESS_KEY. Empty = all enabled detectors.", "default": [], "items": { "type": "string" } }, "allowList": { "title": "Allow list", "type": "array", "description": "Exact values never flagged (e.g. your public support@ address).", "default": [], "items": { "type": "string" } }, "includeFindingValues": { "title": "Include raw values in findings", "type": "boolean", "description": "Off by default: findings carry only a masked preview and offsets, so the dataset holds no raw sensitive values.", "default": false }, "maxDocuments": { "title": "Max documents", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety cap per run.", "default": 1000 }, "maxCharsPerDocument": { "title": "Max characters per document", "minimum": 1000, "maximum": 20000000, "type": "integer", "description": "Longer documents are truncated (row gets truncated=true).", "default": 1000000 }, "purgeInputAfterRun": { "title": "Purge input after run", "type": "boolean", "description": "Delete the INPUT record from the run's key-value store when the run ends, so only the results dataset remains.", "default": true } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }