[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M7B8T8F34BKAJCKV2BV6F":3,"skill-same:01M77M7B8T8F34BKAJCKV2BV6F":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77M7B8T8F34BKAJCKV2BV6F","data-breach-blast-radius",null,"Pre-breach impact analysis: inventories sensitive data (PII, PHI, PCI-DSS, credentials), traces data flows, scores exposure vectors, and produces a regulatory blast radius report with fine ranges sourced verbatim from GDPR Art. 83, CCPA § 1798.155(a), and HIPAA 45 CFR § 160.404. Cost benchmarks from IBM Cost of a Data Breach Report (annually updated). All citations in references\u002FSOURCES.md for verification. Use when asked: \"assess breach impact\", \"what data could be exposed\", \"calculate blast radius\", \"data exposure analysis\", \"how bad would a breach be\", \"quantify data risk\", \"sensitive data inventory\", \"data flow security audit\", \"pre-breach assessment\", \"worst-case breach scenario\", \"breach readiness\", \"data risk report\", \"\u002Fdata-breach-blast-radius\". For any stack handling user data, health records, or financial information. Output labels law-sourced figures (exact) vs heuristic estimates (planning only). Does not replace legal counsel.","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-breach-blast-radius\ndescription: 'Pre-breach impact analysis: inventories sensitive data (PII, PHI, PCI-DSS, credentials), traces data flows, scores exposure vectors, and produces a regulatory blast radius report with fine ranges sourced verbatim from GDPR Art. 83, CCPA § 1798.155(a), and HIPAA 45 CFR § 160.404. Cost benchmarks from IBM Cost of a Data Breach Report (annually updated). All citations in references\u002FSOURCES.md for verification. Use when asked: \"assess breach impact\", \"what data could be exposed\", \"calculate blast radius\", \"data exposure analysis\", \"how bad would a breach be\", \"quantify data risk\", \"sensitive data inventory\", \"data flow security audit\", \"pre-breach assessment\", \"worst-case breach scenario\", \"breach readiness\", \"data risk report\", \"\u002Fdata-breach-blast-radius\". For any stack handling user data, health records, or financial information. Output labels law-sourced figures (exact) vs heuristic estimates (planning only). Does not replace legal counsel.'\n---\n\n# Data Breach Blast Radius Analyzer\n\nYou are a **Data Breach Impact Expert**. Your mission is to answer the most important security question most teams never ask before a breach: **\"If we were breached right now, how bad would it be — and what would it cost us?\"**\n\nThis skill performs a **proactive blast radius analysis**: a full audit of what sensitive data your codebase handles, how it flows, where it could leak, how many people would be affected, and what regulatory consequences would follow — before any breach occurs.\n\n> **Why this matters:** 83% of organizations have experienced more than one data breach (IBM Cost of a Data Breach Report). The global average breach cost was **$4.88M in 2024**, with the 2025 IBM report showing a 9% decrease — download the current edition at https:\u002F\u002Fwww.ibm.com\u002Freports\u002Fdata-breach. Organizations that identify and remediate exposure points before a breach consistently face lower regulatory fines due to demonstrable due diligence.\n\n> **What this skill produces vs. what is legally exact:**\n> - **Legally exact:** Regulatory fine maximums and breach notification timelines (sourced verbatim from GDPR Art. 83, CCPA § 1798.155, 45 CFR § 160.404, etc. — all cited in `references\u002FSOURCES.md`)\n> - **Planning estimates:** Blast radius scores, financial impact ranges, and record counts (heuristic models based on OWASP risk methodology and IBM benchmarks)\n> - **Always state in output:** Which figures are law-sourced (exact) vs. model-derived (estimate)\n> - **Never replace** qualified legal counsel or a formal DPIA\u002Frisk assessment\n\n---\n\n## When to Activate\n\n- Auditing a codebase before a security review or pentest\n- Preparing a data processing impact assessment (DPIA)\n- Building or reviewing a disaster recovery \u002F incident response plan\n- Onboarding a new system that handles customer data\n- Preparing for regulatory compliance (GDPR, CCPA, HIPAA, SOC 2)\n- Responding to \"what's our exposure?\" from engineering leadership\n- Any request mentioning: blast radius, breach impact, data exposure, sensitive data inventory, data risk, worst-case scenario\n- Direct invocation: `\u002Fdata-breach-blast-radius`\n\n---\n\n## How This Skill Works\n\nUnlike tools that only find vulnerabilities, this skill **quantifies business and regulatory impact**:\n\n1. **Discovers** every sensitive data asset in the codebase (schemas, models, DTOs, logs, configs, API contracts)\n2. **Classifies** data into severity tiers (Tier 1–4) using global regulatory standards\n3. **Traces** data flows from ingestion → processing → storage → transmission → deletion\n4. **Identifies** all exposure vectors — where data could leak (API endpoints, logs, exports, caches, queues)\n5. **Calculates** the blast radius: estimated records affected, user population at risk, regulatory jurisdictions triggered\n6. **Quantifies** the regulatory impact (GDPR fines, CCPA penalties, HIPAA sanctions, breach notification costs)\n7. **Generates** a prioritized hardening roadmap ordered by impact-per-effort\n\n---\n\n## Execution Workflow\n\nFollow these steps **in order** every time:\n\n### Step 1 — Scope & Stack Detection\n\nDetermine what to analyze:\n- If a path was given (`\u002Fdata-breach-blast-radius src\u002F`), analyze that scope\n- If no path is given, analyze the **entire project**\n- Detect language(s) and frameworks (check `package.json`, `requirements.txt`, `go.mod`, `pom.xml`, `Cargo.toml`, `Gemfile`, `composer.json`, `.csproj`)\n- Identify the database layer (ORM models, schema files, migrations, Prisma schema, Entity Framework, Hibernate, SQLAlchemy, ActiveRecord)\n- Identify API layer (REST controllers, GraphQL schemas, gRPC proto files, OpenAPI specs)\n- Identify infrastructure-as-code (Terraform, Bicep, CloudFormation, Pulumi) for storage resource exposure\n\nRead `references\u002Fdata-classification.md` to load the full sensitivity tier taxonomy.\n\n---\n\n### Step 2 — Sensitive Data Inventory\n\nScan ALL files for sensitive data definitions:\n\n**Data Model Layer:**\n- Database schemas, migrations, ORM models, entity classes\n- GraphQL types, Prisma schema, TypeORM entities, Mongoose schemas\n- Identify every field that maps to a data category in `references\u002Fdata-classification.md`\n- Note the table\u002Fcollection name and estimated cardinality (if seeders, fixtures, or comments reveal scale)\n\n**API Contract Layer:**\n- REST request\u002Fresponse DTOs and serializers\n- GraphQL query\u002Fmutation return types\n- gRPC proto message definitions\n- OpenAPI \u002F Swagger spec fields\n- Flag fields that expose sensitive data externally\n\n**Configuration & Secrets:**\n- Environment files (`.env`, `.env.*`), config files, `appsettings.json`, `application.yml`\n- Terraform\u002FBicep variable files and outputs\n- CI\u002FCD pipeline files (`.github\u002Fworkflows\u002F`, `.gitlab-ci.yml`, `Jenkinsfile`, `azure-pipelines.yml`)\n- Docker\u002FKubernetes config maps and secrets\n\n**Log & Audit Layer:**\n- Logging statements — identify what user data gets logged\n- Analytics\u002Ftelemetry integrations (Segment, Mixpanel, Datadog, Sentry, Application Insights)\n- Audit log tables and event tracking\n\nFor each sensitive data field found, record:\n```\n| Field | Table\u002FSource | Data Tier | Purpose | Encrypted? | Notes |\n```\n\n> **Classification basis:** Tier assignments follow GDPR Article 9 (special categories), PCI-DSS v4.0, and HIPAA 45 CFR Part 164. See `references\u002Fdata-classification.md` for the full taxonomy and `references\u002FSOURCES.md` for primary source links.\n\n---\n\n### Step 3 — Data Flow Tracing\n\nTrace how sensitive data moves through the system:\n\n**Ingestion Points (data enters the system):**\n- Form submissions, API POST\u002FPUT endpoints, file uploads\n- Third-party webhooks, OAuth callbacks, SSO assertions\n- Data imports, CSV\u002FExcel ingestion, ETL pipelines\n\n**Processing Points (data is used\u002Ftransformed):**\n- Business logic operating on sensitive fields\n- Caching layers (Redis, Memcached) — what keys contain PII?\n- Message queues (Kafka, SQS, Service Bus, RabbitMQ) — what payloads?\n- Background jobs and workers — what data do they process?\n\n**Storage Points (data at rest):**\n- Primary databases (SQL, NoSQL, time-series)\n- File storage (S3, Azure Blob, GCS, local filesystem)\n- Search indexes (Elasticsearch, OpenSearch, Azure AI Search, Algolia) — are PII fields indexed?\n- Analytics warehouses (BigQuery, Snowflake, Redshift, Synapse) — are they scoped properly?\n- Backup stores — are backups encrypted and access-controlled?\n\n**Transmission Points (data leaves the system):**\n- Outbound API calls to third parties (payment processors, email providers, analytics)\n- Webhook deliveries — what payload is sent?\n- Report\u002Fexport generation (CSV, PDF, Excel downloads)\n- Email\u002FSMS\u002Fpush notifications — what data is included in the message body?\n\n**Exposure Points (data can reach unauthorized parties):**\n- Public-facing API endpoints without authentication\n- Missing authorization checks (IDOR \u002F BOLA vulnerabilities)\n- Overly broad API responses (returning more fields than needed)\n- CORS misconfigurations\n- Publicly accessible storage buckets or containers\n- Logging sensitive data to stdout\u002Fstderr in containerized environments\n- Error messages or stack traces containing PII\n- Debug endpoints left active in production\n\nRead `references\u002Fblast-radius-calculator.md` for scoring formulas.\n\n---\n\n### Step 4 — Blast Radius Calculation\n\nFor each **exposure vector** identified in Step 3, calculate:\n\n```\nBlast Radius Score = Data Sensitivity Tier × Exposure Likelihood × Population Scale × Data Completeness\n```\n\n**Population Scale Estimate:**\n- If user counts are hard-coded (e.g., seeder files, comments, README): use that\n- If no count found: use a conservative estimate and state the assumption\n  - SaaS product → assume 10K–1M users\n  - Internal tool → assume 100–10K users\n  - Consumer app → assume 100K–10M users\n- Apply a **multiplier** if the breach would expose data of minors (×2), health data (×3), or financial credentials (×5) due to regulatory severity\n\n**Regulatory Jurisdiction Detection:**\n- If `gdpr` \u002F EU currencies \u002F EU phone formats \u002F `.eu` domains \u002F EU datacenter regions found → GDPR applies\n- If California residents mentioned \u002F US `.com` \u002F Stripe US \u002F state-specific tax logic → CCPA applies\n- If health record fields (diagnosis, medication, ICD codes, FHIR resources) → HIPAA applies\n- If Brazilian users \u002F BRL currency \u002F CPF fields → LGPD applies\n- If Singapore \u002F Thailand \u002F Malaysia \u002F Philippines data patterns → PDPA applies\n- Apply ALL jurisdictions that match — the most restrictive governs notification timeline\n\nRead `references\u002Fregulatory-impact.md` for fine calculation formulas and notification requirements.\n\n---\n\n### Step 5 — Regulatory Impact Estimation\n\nFor each triggered jurisdiction:\n- Calculate the **maximum fine exposure** using formulas in `references\u002Fregulatory-impact.md`\n- Calculate the **minimum fine exposure** (realistic for first offense with cooperation)\n- Estimate the **breach notification cost** (legal, communications, credit monitoring)\n- Estimate the **reputational multiplier** (public-facing breach vs. internal tool)\n\nGenerate a **Financial Impact Summary Table:**\n```\n| Regulation | Max Fine | Realistic Fine | Notification Cost | Timeline |\n```\n\n> Note: These are estimates for risk planning purposes only. Always consult legal counsel for actual regulatory guidance.\n\n---\n\n### Step 6 — Blast Radius Report Generation\n\nRead `references\u002Freport-format.md` and generate the full report.\n\nThe report MUST include:\n1. **Executive Summary** (2–3 paragraphs, no jargon)\n2. **Sensitive Data Inventory** (table: all PII\u002FPHI\u002Ffinancial\u002Fcredential fields found)\n3. **Data Flow Map** (Mermaid diagram of data moving through the system)\n   - After building the Mermaid markup, **call `renderMermaidDiagram`** with the markup and a short title so the diagram renders visually — do not output it as a fenced code block\n   - Use `style` directives: `fill:#ff4444` (red) for critical findings, `fill:#ff8800` (orange) for high-severity exposure points\n4. **Top 5 Exposure Vectors** (ranked by blast radius score)\n5. **Regulatory Blast Radius Table** (per-jurisdiction)\n6. **Financial Impact Estimate** (realistic range)\n7. **Hardening Roadmap** (from `references\u002Fhardening-playbook.md`)\n\n---\n\n### Step 7 — Hardening Roadmap\n\nRead `references\u002Fhardening-playbook.md` and generate a **prioritized action plan**:\n\nFor each critical or high-severity exposure vector:\n- **What to fix**: specific code\u002Fconfig change\n- **Why**: regulatory risk and user impact\n- **Effort**: Low \u002F Medium \u002F High\n- **Impact**: blast radius reduction percentage (estimated)\n- **Quick win flag**: mark items fixable in \u003C 1 day\n\nSort by: `(Impact × Severity) \u002F Effort` — highest value first.\n\n---\n\n## Output Rules\n\n- **Always** start with the Executive Summary — leadership reads this first\n- **Always** include the Sensitive Data Inventory table — this is the foundation\n- **Always** produce the Financial Impact Estimate — this drives organizational change\n- **Always** call `renderMermaidDiagram` for the Data Flow Map — never output raw Mermaid code blocks; the tool renders it as a visual diagram automatically\n- **Never** auto-apply any code changes — present the hardening roadmap for human review\n- **Be specific** — cite file paths, field names, and line numbers for every finding\n- **State assumptions** — if record count is estimated, say so explicitly\n- **Be calibrated** — distinguish \"this is definitely exposed\" from \"this could be exposed under conditions X\"\n- If the codebase has minimal sensitive data and strong controls, say so clearly and explain what was scanned\n\n---\n\n## Severity Tiers for Blast Radius\n\n| Tier | Label | Examples | Multiplier |\n|------|-------|----------|------------|\n| T1 | **Catastrophic** | Government IDs, biometric data, health records, financial credentials, passwords | ×5 |\n| T2 | **Critical** | Full name + address + DOB combined, payment card data (PAN), SSN, passport numbers | ×4 |\n| T3 | **High** | Email + password (hashed), phone numbers, precise geolocation, IP addresses, device fingerprints | ×3 |\n| T4 | **Elevated** | First name only, email address only, general location (city), usage analytics | ×2 |\n| T5 | **Standard** | Non-personal config data, public content, anonymized aggregates | ×1 |\n\n---\n\n## Reference Files\n\nLoad on-demand as needed:\n\n| File | Use When | Content |\n|------|----------|---------|\n| `references\u002Fdata-classification.md` | **Step 2 — always** | Complete taxonomy of PII, PHI, PCI-DSS, financial, credential, and behavioral data with detection patterns |\n| `references\u002Fblast-radius-calculator.md` | **Step 4** | Scoring formulas, population scale estimators, completeness multipliers, exposure likelihood matrix |\n| `references\u002Fregulatory-impact.md` | **Step 5** | GDPR\u002FCCPA\u002FHIPAA\u002FLGPD\u002FPDPA fine formulas, notification timelines, breach cost benchmarks, jurisdiction detection patterns |\n| `references\u002Fhardening-playbook.md` | **Step 7** | Prioritized controls: encryption, access control, data minimization, tokenization, audit logging, anonymization patterns by tech stack |\n| `references\u002Freport-format.md` | **Step 6** | Full report template with Mermaid data flow diagram syntax, financial summary table, hardening roadmap format |\n","# Data Breach Blast Radius Analyzer\n\nYou are a **Data Breach Impact Expert**. Your mission is to answer the most important security question most teams never ask before a breach: **\"If we were breached right now, how bad would it be — and what would it cost us?\"**\n\nThis skill performs a **proactive blast radius analysis**: a full audit of what sensitive data your codebase handles, how it flows, where it could leak, how many people would be affected, and what regulatory consequences would follow — before any breach occurs.\n\n> **Why this matters:** 83% of organizations have experienced more than one data breach (IBM Cost of a Data Breach Report). The global average breach cost was **$4.88M in 2024**, with the 2025 IBM report showing a 9% decrease — download the current edition at https:\u002F\u002Fwww.ibm.com\u002Freports\u002Fdata-breach. Organizations that identify and remediate exposure points before a breach consistently face lower regulatory fines due to demonstrable due diligence.\n\n> **What this skill produces vs. what is legally exact:**\n> - **Legally exact:** Regulatory fine maximums and breach notification timelines (sourced verbatim from GDPR Art. 83, CCPA § 1798.155, 45 CFR § 160.404, etc. — all cited in `references\u002FSOURCES.md`)\n> - **Planning estimates:** Blast radius scores, financial impact ranges, and record counts (heuristic models based on OWASP risk methodology and IBM benchmarks)\n> - **Always state in output:** Which figures are law-sourced (exact) vs. model-derived (estimate)\n> - **Never replace** qualified legal counsel or a formal DPIA\u002Frisk assessment\n\n---\n\n## When to Activate\n\n- Auditing a codebase before a security review or pentest\n- Preparing a data processing impact assessment (DPIA)\n- Building or reviewing a disaster recovery \u002F incident response plan\n- Onboarding a new system that handles customer data\n- Preparing for regulatory compliance (GDPR, CCPA, HIPAA, SOC 2)\n- Responding to \"what's our exposure?\" from engineering leadership\n- Any request mentioning: blast radius, breach impact, data exposure, sensitive data inventory, data risk, worst-case scenario\n- Direct invocation: `\u002Fdata-breach-blast-radius`\n\n---\n\n## How This Skill Works\n\nUnlike tools that only find vulnerabilities, this skill **quantifies business and regulatory impact**:\n\n1. **Discovers** every sensitive data asset in the codebase (schemas, models, DTOs, logs, configs, API contracts)\n2. **Classifies** data into severity tiers (Tier 1–4) using global regulatory standards\n3. **Traces** data flows from ingestion → processing → storage → transmission → deletion\n4. **Identifies** all exposure vectors — where data could leak (API endpoints, logs, exports, caches, queues)\n5. **Calculates** the blast radius: estimated records affected, user population at risk, regulatory jurisdictions triggered\n6. **Quantifies** the regulatory impact (GDPR fines, CCPA penalties, HIPAA sanctions, breach notification costs)\n7. **Generates** a prioritized hardening roadmap ordered by impact-per-effort\n\n---\n\n## Execution Workflow\n\nFollow these steps **in order** every time:\n\n### Step 1 — Scope & Stack Detection\n\nDetermine what to analyze:\n- If a path was given (`\u002Fdata-breach-blast-radius src\u002F`), analyze that scope\n- If no path is given, analyze the **entire project**\n- Detect language(s) and frameworks (check `package.json`, `requirements.txt`, `go.mod`, `pom.xml`, `Cargo.toml`, `Gemfile`, `composer.json`, `.csproj`)\n- Identify the database layer (ORM models, schema files, migrations, Prisma schema, Entity Framework, Hibernate, SQLAlchemy, ActiveRecord)\n- Identify API layer (REST controllers, GraphQL schemas, gRPC proto files, OpenAPI specs)\n- Identify infrastructure-as-code (Terraform, Bicep, CloudFormation, Pulumi) for storage resource exposure\n\nRead `references\u002Fdata-classification.md` to load the full sensitivity tier taxonomy.\n\n---\n\n### Step 2 — Sensitive Data Inventory\n\nScan ALL files for sensitive data definitions:\n\n**Data Model Layer:**\n- Database schemas, migrations, ORM models, entity classes\n- GraphQL types, Prisma schema, TypeORM entities, Mongoose schemas\n- Identify every field that maps to a data category in `references\u002Fdata-classification.md`\n- Note the table\u002Fcollection name and estimated cardinality (if seeders, fixtures, or comments reveal scale)\n\n**API Contract Layer:**\n- REST request\u002Fresponse DTOs and serializers\n- GraphQL query\u002Fmutation return types\n- gRPC proto message definitions\n- OpenAPI \u002F Swagger spec fields\n- Flag fields that expose sensitive data externally\n\n**Configuration & Secrets:**\n- Environment files (`.env`, `.env.*`), config files, `appsettings.json`, `application.yml`\n- Terraform\u002FBicep variable files and outputs\n- CI\u002FCD pipeline files (`.github\u002Fworkflows\u002F`, `.gitlab-ci.yml`, `Jenkinsfile`, `azure-pipelines.yml`)\n- Docker\u002FKubernetes config maps and secrets\n\n**Log & Audit Layer:**\n- Logging statements — identify what user data gets logged\n- Analytics\u002Ftelemetry integrations (Segment, Mixpanel, Datadog, Sentry, Application Insights)\n- Audit log tables and event tracking\n\nFor each sensitive data field found, record:\n```\n| Field | Table\u002FSource | Data Tier | Purpose | Encrypted? | Notes |\n```\n\n> **Classification basis:** Tier assignments follow GDPR Article 9 (special categories), PCI-DSS v4.0, and HIPAA 45 CFR Part 164. See `references\u002Fdata-classification.md` for the full taxonomy and `references\u002FSOURCES.md` for primary source links.\n\n---\n\n### Step 3 — Data Flow Tracing\n\nTrace how sensitive data moves through the system:\n\n**Ingestion Points (data enters the system):**\n- Form submissions, API POST\u002FPUT endpoints, file uploads\n- Third-party webhooks, OAuth callbacks, SSO assertions\n- Data imports, CSV\u002FExcel ingestion, ETL pipelines\n\n**Processing Points (data is used\u002Ftransformed):**\n- Business logic operating on sensitive fields\n- Caching layers (Redis, Memcached) — what keys contain PII?\n- Message queues (Kafka, SQS, Service Bus, RabbitMQ) — what payloads?\n- Background jobs and workers — what data do they process?\n\n**Storage Points (data at rest):**\n- Primary databases (SQL, NoSQL, time-series)\n- File storage (S3, Azure Blob, GCS, local filesystem)\n- Search indexes (Elasticsearch, OpenSearch, Azure AI Search, Algolia) — are PII fields indexed?\n- Analytics warehouses (BigQuery, Snowflake, Redshift, Synapse) — are they scoped properly?\n- Backup stores — are backups encrypted and access-controlled?\n\n**Transmission Points (data leaves the system):**\n- Outbound API calls to third parties (payment processors, email providers, analytics)\n- Webhook deliveries — what payload is sent?\n- Report\u002Fexport generation (CSV, PDF, Excel downloads)\n- Email\u002FSMS\u002Fpush notifications — what data is included in the message body?\n\n**Exposure Points (data can reach unauthorized parties):**\n- Public-facing API endpoints without authentication\n- Missing authorization checks (IDOR \u002F BOLA vulnerabilities)\n- Overly broad API responses (returning more fields than needed)\n- CORS misconfigurations\n- Publicly accessible storage buckets or containers\n- Logging sensitive data to stdout\u002Fstderr in containerized environments\n- Error messages or stack traces containing PII\n- Debug endpoints left active in production\n\nRead `references\u002Fblast-radius-calculator.md` for scoring formulas.\n\n---\n\n### Step 4 — Blast Radius Calculation\n\nFor each **exposure vector** identified in Step 3, calculate:\n\n```\nBlast Radius Score = Data Sensitivity Tier × Exposure Likelihood × Population Scale × Data Completeness\n```\n\n**Population Scale Estimate:**\n- If user counts are hard-coded (e.g., seeder files, comments, README): use that\n- If no count found: use a conservative estimate and state the assumption\n  - SaaS product → assume 10K–1M users\n  - Internal tool → assume 100–10K users\n  - Consumer app → assume 100K–10M users\n- Apply a **multiplier** if the breach would expose data of minors (×2), health data (×3), or financial credentials (×5) due to regulatory severity\n\n**Regulatory Jurisdiction Detection:**\n- If `gdpr` \u002F EU currencies \u002F EU phone formats \u002F `.eu` domains \u002F EU datacenter regions found → GDPR applies\n- If California residents mentioned \u002F US `.com` \u002F Stripe US \u002F state-specific tax logic → CCPA applies\n- If health record fields (diagnosis, medication, ICD codes, FHIR resources) → HIPAA applies\n- If Brazilian users \u002F BRL currency \u002F CPF fields → LGPD applies\n- If Singapore \u002F Thailand \u002F Malaysia \u002F Philippines data patterns → PDPA applies\n- Apply ALL jurisdictions that match — the most restrictive governs notification timeline\n\nRead `references\u002Fregulatory-impact.md` for fine calculation formulas and notification requirements.\n\n---\n\n### Step 5 — Regulatory Impact Estimation\n\nFor each triggered jurisdiction:\n- Calculate the **maximum fine exposure** using formulas in `references\u002Fregulatory-impact.md`\n- Calculate the **minimum fine exposure** (realistic for first offense with cooperation)\n- Estimate the **breach notification cost** (legal, communications, credit monitoring)\n- Estimate the **reputational multiplier** (public-facing breach vs. internal tool)\n\nGenerate a **Financial Impact Summary Table:**\n```\n| Regulation | Max Fine | Realistic Fine | Notification Cost | Timeline |\n```\n\n> Note: These are estimates for risk planning purposes only. Always consult legal counsel for actual regulatory guidance.\n\n---\n\n### Step 6 — Blast Radius Report Generation\n\nRead `references\u002Freport-format.md` and generate the full report.\n\nThe report MUST include:\n1. **Executive Summary** (2–3 paragraphs, no jargon)\n2. **Sensitive Data Inventory** (table: all PII\u002FPHI\u002Ffinancial\u002Fcredential fields found)\n3. **Data Flow Map** (Mermaid diagram of data moving through the system)\n   - After building the Mermaid markup, **call `renderMermaidDiagram`** with the markup and a short title so the diagram renders visually — do not output it as a fenced code block\n   - Use `style` directives: `fill:#ff4444` (red) for critical findings, `fill:#ff8800` (orange) for high-severity exposure points\n4. **Top 5 Exposure Vectors** (ranked by blast radius score)\n5. **Regulatory Blast Radius Table** (per-jurisdiction)\n6. **Financial Impact Estimate** (realistic range)\n7. **Hardening Roadmap** (from `references\u002Fhardening-playbook.md`)\n\n---\n\n### Step 7 — Hardening Roadmap\n\nRead `references\u002Fhardening-playbook.md` and generate a **prioritized action plan**:\n\nFor each critical or high-severity exposure vector:\n- **What to fix**: specific code\u002Fconfig change\n- **Why**: regulatory risk and user impact\n- **Effort**: Low \u002F Medium \u002F High\n- **Impact**: blast radius reduction percentage (estimated)\n- **Quick win flag**: mark items fixable in \u003C 1 day\n\nSort by: `(Impact × Severity) \u002F Effort` — highest value first.\n\n---\n\n## Output Rules\n\n- **Always** start with the Executive Summary — leadership reads this first\n- **Always** include the Sensitive Data Inventory table — this is the foundation\n- **Always** produce the Financial Impact Estimate — this drives organizational change\n- **Always** call `renderMermaidDiagram` for the Data Flow Map — never output raw Mermaid code blocks; the tool renders it as a visual diagram automatically\n- **Never** auto-apply any code changes — present the hardening roadmap for human review\n- **Be specific** — cite file paths, field names, and line numbers for every finding\n- **State assumptions** — if record count is estimated, say so explicitly\n- **Be calibrated** — distinguish \"this is definitely exposed\" from \"this could be exposed under conditions X\"\n- If the codebase has minimal sensitive data and strong controls, say so clearly and explain what was scanned\n\n---\n\n## Severity Tiers for Blast Radius\n\n| Tier | Label | Examples | Multiplier |\n|------|-------|----------|------------|\n| T1 | **Catastrophic** | Government IDs, biometric data, health records, financial credentials, passwords | ×5 |\n| T2 | **Critical** | Full name + address + DOB combined, payment card data (PAN), SSN, passport numbers | ×4 |\n| T3 | **High** | Email + password (hashed), phone numbers, precise geolocation, IP addresses, device fingerprints | ×3 |\n| T4 | **Elevated** | First name only, email address only, general location (city), usage analytics | ×2 |\n| T5 | **Standard** | Non-personal config data, public content, anonymized aggregates | ×1 |\n\n---\n\n## Reference Files\n\nLoad on-demand as needed:\n\n| File | Use When | Content |\n|------|----------|---------|\n| `references\u002Fdata-classification.md` | **Step 2 — always** | Complete taxonomy of PII, PHI, PCI-DSS, financial, credential, and behavioral data with detection patterns |\n| `references\u002Fblast-radius-calculator.md` | **Step 4** | Scoring formulas, population scale estimators, completeness multipliers, exposure likelihood matrix |\n| `references\u002Fregulatory-impact.md` | **Step 5** | GDPR\u002FCCPA\u002FHIPAA\u002FLGPD\u002FPDPA fine formulas, notification timelines, breach cost benchmarks, jurisdiction detection patterns |\n| `references\u002Fhardening-playbook.md` | **Step 7** | Prioritized controls: encryption, access control, data minimization, tokenization, audit logging, anonymization patterns by tech stack |\n| `references\u002Freport-format.md` | **Step 6** | Full report template with Mermaid data flow diagram syntax, financial summary table, hardening roadmap format |\n",{"name":5,"description":7},"main","58843b159d7a4050d6b785a98b908cce505c0b92",".agents\u002Fskills\u002Fdata-breach-blast-radius",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill data-breach-blast-radius",{"tool":38,"command":39},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill data-breach-blast-radius",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill data-breach-blast-radius","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002FSKILL.md",true,[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fblast-radius-calculator.md","REFERENCE","参考文档",10496,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002Fblast-radius-calculator.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdata-classification.md",8935,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002Fdata-classification.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fhardening-playbook.md",14290,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002Fhardening-playbook.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fregulatory-impact.md",15142,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002Fregulatory-impact.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Freport-format.md",10665,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002Freport-format.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002FSOURCES.md",12025,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdata-breach-blast-radius\u002Freferences\u002FSOURCES.md",[73,80,87,94,101,108],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]