Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Python agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
docs(playbooks): the phishing playbook's retraction step is still a no-op, and now says where the real purge is
Beenu Aroradf3b6b96df52
diff --git a/apps/web/public/marketplace/index.json b/apps/web/public/marketplace/index.jsonindex fa60978cf..a92fed289 100644--- a/apps/web/public/marketplace/index.json+++ b/apps/web/public/marketplace/index.json@@ -1,7 +1,7 @@{"$schema": "https://example.com/schemas/marketplace/v1.json","version": "1.0.0",- "generated": "2026-10-10T01:22:53Z",+ "generated": "2026-10-11T02:59:14Z","categories": [{"id": "playbooks",@@ -236865,7 +236865,7 @@"id": "phishing-investigation-v1","type": "playbook","name": "Phishing: Email Investigation & Remediation",- "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped.",+ "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step here still requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped. Depth 7.1 added a real mailbox purge, and it is not this step: report the message to POST /phishing/reports and purge the campaign through POST /phishing/campaigns/{id}/purge, which dispatches purge_email once per recipient under the capability contract, verifies each mailbox and can be reversed. That path needs AISOC_FEATURE_MAILBOX_REMEDIATION and a Microsoft 365 or Google Workspace connector; it is not reachable as a playbook step because the engine has no purge_email step type.","version": "1.0.0","author": "Beenu - [email protected]","tags": [@@ -236887,7 +236887,7 @@"pack": true,"enabled": true,"path": "playbooks/packs/v1/phishing/phishing-investigation.playbook.json",- "sha256": "73f354344458fe6ed95f28835b5cc40c045c67716f5c56f909b6df3b8406ef7a"+ "sha256": "09377aedb0296894ec461caad295b3596a8ea9cdf90151463df094698ca85a27"},{"id": "phishing-response-v1",diff --git a/marketplace/index.json b/marketplace/index.jsonindex fa60978cf..a92fed289 100644--- a/marketplace/index.json+++ b/marketplace/index.json@@ -1,7 +1,7 @@{"$schema": "https://example.com/schemas/marketplace/v1.json","version": "1.0.0",- "generated": "2026-10-10T01:22:53Z",+ "generated": "2026-10-11T02:59:14Z","categories": [{"id": "playbooks",@@ -236865,7 +236865,7 @@"id": "phishing-investigation-v1","type": "playbook","name": "Phishing: Email Investigation & Remediation",- "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped.",+ "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step here still requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped. Depth 7.1 added a real mailbox purge, and it is not this step: report the message to POST /phishing/reports and purge the campaign through POST /phishing/campaigns/{id}/purge, which dispatches purge_email once per recipient under the capability contract, verifies each mailbox and can be reversed. That path needs AISOC_FEATURE_MAILBOX_REMEDIATION and a Microsoft 365 or Google Workspace connector; it is not reachable as a playbook step because the engine has no purge_email step type.","version": "1.0.0","author": "Beenu - [email protected]","tags": [@@ -236887,7 +236887,7 @@"pack": true,"enabled": true,"path": "playbooks/packs/v1/phishing/phishing-investigation.playbook.json",- "sha256": "73f354344458fe6ed95f28835b5cc40c045c67716f5c56f909b6df3b8406ef7a"+ "sha256": "09377aedb0296894ec461caad295b3596a8ea9cdf90151463df094698ca85a27"},{"id": "phishing-response-v1",diff --git a/playbooks/packs/v1/phishing/phishing-investigation.playbook.json b/playbooks/packs/v1/phishing/phishing-investigation.playbook.jsonindex eba28a8eb..c4f282cc8 100644--- a/playbooks/packs/v1/phishing/phishing-investigation.playbook.json+++ b/playbooks/packs/v1/phishing/phishing-investigation.playbook.json@@ -1,7 +1,7 @@{"id": "phishing-investigation-v1","name": "Phishing: Email Investigation & Remediation",- "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped.",+ "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step here still requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped. Depth 7.1 added a real mailbox purge, and it is not this step: report the message to POST /phishing/reports and purge the campaign through POST /phishing/campaigns/{id}/purge, which dispatches purge_email once per recipient under the capability contract, verifies each mailbox and can be reversed. That path needs AISOC_FEATURE_MAILBOX_REMEDIATION and a Microsoft 365 or Google Workspace connector; it is not reachable as a playbook step because the engine has no purge_email step type.","version": "1.0.0","author": "Beenu - [email protected]","tags": [@@ -76,7 +76,7 @@},{"id": "retract",- "name": "Retract the message via the tenant's email gateway (needs EMAIL_GATEWAY_URL; no-op when unset)",+ "name": "Retract the message via the tenant's email gateway (needs EMAIL_GATEWAY_URL; no-op when unset — the real mailbox purge is POST /phishing/campaigns/{id}/purge, not this step)","type": "http","params": {"url": "${EMAIL_GATEWAY_URL}/v1/messages/retract",diff --git a/services/agents/app/playbook/packs/v1/phishing/phishing-investigation.playbook.json b/services/agents/app/playbook/packs/v1/phishing/phishing-investigation.playbook.jsonindex eba28a8eb..c4f282cc8 100644--- a/services/agents/app/playbook/packs/v1/phishing/phishing-investigation.playbook.json+++ b/services/agents/app/playbook/packs/v1/phishing/phishing-investigation.playbook.json@@ -1,7 +1,7 @@{"id": "phishing-investigation-v1","name": "Phishing: Email Investigation & Remediation",- "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped.",+ "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step here still requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped. Depth 7.1 added a real mailbox purge, and it is not this step: report the message to POST /phishing/reports and purge the campaign through POST /phishing/campaigns/{id}/purge, which dispatches purge_email once per recipient under the capability contract, verifies each mailbox and can be reversed. That path needs AISOC_FEATURE_MAILBOX_REMEDIATION and a Microsoft 365 or Google Workspace connector; it is not reachable as a playbook step because the engine has no purge_email step type.","version": "1.0.0","author": "Beenu - [email protected]","tags": [@@ -76,7 +76,7 @@},{"id": "retract",- "name": "Retract the message via the tenant's email gateway (needs EMAIL_GATEWAY_URL; no-op when unset)",+ "name": "Retract the message via the tenant's email gateway (needs EMAIL_GATEWAY_URL; no-op when unset — the real mailbox purge is POST /phishing/campaigns/{id}/purge, not this step)","type": "http","params": {"url": "${EMAIL_GATEWAY_URL}/v1/messages/retract",diff --git a/services/api/app/data/marketplace/index.json b/services/api/app/data/marketplace/index.jsonindex fa60978cf..a92fed289 100644--- a/services/api/app/data/marketplace/index.json+++ b/services/api/app/data/marketplace/index.json@@ -1,7 +1,7 @@{"$schema": "https://example.com/schemas/marketplace/v1.json","version": "1.0.0",- "generated": "2026-10-10T01:22:53Z",+ "generated": "2026-10-11T02:59:14Z","categories": [{"id": "playbooks",@@ -236865,7 +236865,7 @@"id": "phishing-investigation-v1","type": "playbook","name": "Phishing: Email Investigation & Remediation",- "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped.",+ "description": "Triggered by a phishing alert from an email gateway or a user report. Extracts IOCs, blocks the sender domain, and resets credentials that may have been compromised. The retraction step here still requires EMAIL_GATEWAY_URL, which no compose file or .env.example sets, so on a default deployment the message is NOT retracted and the step is skipped. Depth 7.1 added a real mailbox purge, and it is not this step: report the message to POST /phishing/reports and purge the campaign through POST /phishing/campaigns/{id}/purge, which dispatches purge_email once per recipient under the capability contract, verifies each mailbox and can be reversed. That path needs AISOC_FEATURE_MAILBOX_REMEDIATION and a Microsoft 365 or Google Workspace connector; it is not reachable as a playbook step because the engine has no purge_email step type.","version": "1.0.0","author": "Beenu - [email protected]","tags": [@@ -236887,7 +236887,7 @@"pack": true,"enabled": true,"path": "playbooks/packs/v1/phishing/phishing-investigation.playbook.json",- "sha256": "73f354344458fe6ed95f28835b5cc40c045c67716f5c56f909b6df3b8406ef7a"+ "sha256": "09377aedb0296894ec461caad295b3596a8ea9cdf90151463df094698ca85a27"},{"id": "phishing-response-v1",