[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7C2J288X98XB65ABMWVGK":3,"skill-same:01M7D7C2J288X98XB65ABMWVGK":69},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":28,"commitSha":29,"skillDirectory":5,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7D7C2J288X98XB65ABMWVGK","google-cloud-scc-query",null,"Queries and retrieves active security findings, external exposures, toxic combinations, vulnerabilities, threats, and sensitive data risks from Security Command Center on Google Cloud. Use when retrieving details for a security finding by its name, validating finding scope (e.g., verifying findingClass is TOXIC_COMBINATION, VULNERABILITY, EXTERNAL_EXPOSURE, or THREAT), or fetching finding details for triage. Don't use to draft remediations, apply patches, or execute configurations.","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: google-cloud-scc-query\nmetadata:\n  version: 1.0.2\n  category: Security\ndescription: Queries and retrieves active security findings, external exposures, toxic\n  combinations, vulnerabilities, threats, and sensitive data risks from Security Command\n  Center on Google Cloud. Use when retrieving details for a security finding by its\n  name, validating finding scope (e.g., verifying findingClass is TOXIC_COMBINATION,\n  VULNERABILITY, EXTERNAL_EXPOSURE, or THREAT), or fetching finding details for triage.\n  Don't use to draft remediations, apply patches, or execute configurations.\n---\n\n# Security Command Center Query Skill on Google Cloud\n\nProvides guidelines and read-only `gcloud` CLI command patterns for querying and\nretrieving security findings, external exposures, toxic combinations,\nvulnerabilities, threats, and sensitive data risks from Security Command Center\non Google Cloud.\n\n> [!IMPORTANT] There is NO `gcloud scc findings describe` command (`Invalid\n> choice: 'describe'`). To retrieve details for a specific finding by its name,\n> always use `gcloud scc findings list` with a filter on `name`.\n\n## Usage Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n--------------------------------------------------------------------------------\n\n## Core Execution Rules\n\n1.  **Read-Only & Zero-Speculation (Parent Scope Required)**: Keep all\n    executions strictly read-only. Every `gcloud scc findings list` or `group`\n    command strictly requires an explicit `{parent}` scope\n    (`organizations\u002F{id}`, `projects\u002F{id}`, or `folders\u002F{id}`). If the parent\n    scope is missing from the prompt and cannot be inferred from a full finding\n    name, **DO NOT run any `gcloud` commands** (do not execute queries without\n    parent, and never inspect `gcloud config`). Halt immediately before\n    executing commands and ask the user for the parent resource scope.\n2.  **Bounded Execution & No Runaway Loops**:\n    -   Limit tool calls to what is strictly necessary to complete the query\n        (typically 1 call for direct queries, or 2 calls for List → Deep Dive\n        workflows).\n    -   If a command fails due to permission\u002Fauth errors, or if a specific\n        finding query returns `[]`, halt immediately. Do not attempt blind\n        brute-force retries with different flags, and never search the local\n        workspace for credentials.\n3.  **Immediate Halt on Errors**: If any command fails with `PERMISSION_DENIED`,\n    `IAM_PERMISSION_DENIED`, credential expiration, or network timeouts, halt\n    immediately and report the verbatim error message. Do not search the\n    workspace for credentials or run diagnostic loops.\n4.  **Ambiguous or Multiple Findings**: If multiple finding names are provided\n    when a single finding report is requested, or if listing returns multiple\n    findings, do not investigate all of them or unilaterally pick one. Halt\n    immediately without running queries and ask the user to clarify which\n    specific finding name they want details for. If zero findings are returned\n    from a query, report that no active findings exist and halt immediately.\n5.  **Do Not Query Attack Path Resources**: Analyze only the data present in the\n    Security Command Center finding JSON payload. Do not run commands to\n    describe, verify, or query underlying Google Cloud resources (such as VMs,\n    Cloud Storage buckets, service accounts, or IAM policies).\n6.  **Parent Scope Resolution**:\n    -   For listing and grouping, format the parent resource path as\n        `organizations\u002F{org_id}`, `projects\u002F{project_id}`, or\n        `folders\u002F{folder_id}`.\n    -   For deep dive queries on a specific finding name, extract the `{parent}`\n        resource prefix before `\u002Fsources\u002F...`:\n        -   `organizations\u002F{org_id}\u002Fsources\u002F...` → `{parent}` is\n            `organizations\u002F{org_id}`\n        -   `folders\u002F{folder_id}\u002Fsources\u002F...` → `{parent}` is\n            `folders\u002F{folder_id}`\n        -   `projects\u002F{project_id}\u002Fsources\u002F...` → `{parent}` is\n            `projects\u002F{project_id}` Extract the parent prefix regardless of\n            whether the finding resource name is global (4-segment) or\n            location-qualified (5-segment with `\u002Flocations\u002F{location}\u002F`).\n            Execute the deep dive query using the extracted `{parent}`. Do not\n            reject or halt on project- or folder-level findings.\n\n--------------------------------------------------------------------------------\n\n## Data Residency & Regional Endpoints\n\nWhen Data Residency (DRZ) is enabled, findings are stored and accessible only\nwithin their designated regional location (`us`, `eu`, or `me-central2`).\nQueries across different locations do not return findings from other regions.\n\n### 1. Location Parameterization\n\nAll `gcloud scc findings` commands require specifying the target location via\n`--location={location}`:\n\n-   **Default**: `global` (used when data residency is not enabled or for global\n    findings).\n-   **Supported Regional Locations**:\n    -   `us` (United States multi-region)\n    -   `eu` (European Union multi-region)\n    -   `me-central2` (Kingdom of Saudi Arabia regional location)\n\n### 2. API Endpoint Overrides\n\nWhen data residency (DRZ) is enabled for an organization in a regional location\n(`us`, `eu`, or `me-central2`), configure the regional API endpoint override\nbefore executing finding queries:\n\n```bash\ngcloud config set api_endpoint_overrides\u002Fsecuritycenter https:\u002F\u002Fsecuritycenter.{LOCATION}.rep.googleapis.com\u002F\n```\n\nExample for the European Union (`eu`) region:\n\n```bash\ngcloud config set api_endpoint_overrides\u002Fsecuritycenter https:\u002F\u002Fsecuritycenter.eu.rep.googleapis.com\u002F\n```\n\nTo reset the endpoint back to default global routing:\n\n```bash\ngcloud config unset api_endpoint_overrides\u002Fsecuritycenter\n```\n\n### 3. Location-Qualified Finding Resource Names\n\nRegional finding resource names include the `\u002Flocations\u002F{location}\u002F` path\nsegment:\n\n-   Organization-level:\n    `organizations\u002F{org_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n-   Folder-level:\n    `folders\u002F{folder_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n-   Project-level:\n    `projects\u002F{project_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n\nWhen performing a Deep Dive on a location-qualified finding name:\n\n1.  Extract the `{parent}` scope (the prefix before `\u002Fsources\u002F...`, e.g.,\n    `organizations\u002F{org_id}`).\n2.  Extract the `{location}` from `\u002Flocations\u002F{location}\u002F` (e.g., `eu`, `us`,\n    `me-central2`). If not present in the finding name, default to `global` (or\n    the user-specified location).\n3.  Execute the query with `--location={location}` and\n    `--filter=\"name=\\\"{finding_name}\\\"\"`.\n\n--------------------------------------------------------------------------------\n\n## Intent-Based Query Strategies\n\n### 1. Deep Dive (Specific Finding Details)\n\n**Intent**: User provides a specific finding name or explicitly asks to retrieve\nall details for one finding. \\\n**Action**: Execute `gcloud scc findings list` with a strict filter on `name`\nand NO `--field-mask` to retrieve the complete JSON payload. Specify\n`--location={location}` (default `global` unless a regional location is\nindicated or present in the finding name).\n\n```bash\ngcloud scc findings list {parent} \\\n  --location={location} \\\n  --filter=\"name=\\\"{finding_name}\\\"\" \\\n  --format=\"json\" --limit=1\n```\n\n### 2. Listing (Filtered Projection)\n\n**Intent**: User wants to list active findings matching criteria without pulling\nfull nested payloads. \\\n**Action**: Use `--field-mask` projection to restrict output size. Specify\n`--location={location}` (default `global` unless querying a specific region).\n\n```bash\ngcloud scc findings list {parent} \\\n  --location={location} \\\n  --filter=\"{filter_expression}\" \\\n  --field-mask=\"finding.name,finding.parentDisplayName,finding.findingClass,finding.category,finding.state,finding.eventTime,finding.severity,finding.resourceName\" \\\n  --format=\"json\" --order-by=\"severity,event_time desc\" --limit=100\n```\n\n| Intent \u002F Target Finding Class | `--filter` Expression                      |\n| :---------------------------- | :----------------------------------------- |\n| **All Active Findings**       | `state=\"ACTIVE\"`                           |\n| **Vulnerabilities**           | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"VULNERABILITY\"`              :\n| **Misconfigurations**         | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"MISCONFIGURATION\"`           :\n| **Toxic Combinations**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"TOXIC_COMBINATION\"`          :\n| **External Exposures**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"EXTERNAL_EXPOSURE\"`          :\n| **Threats**                   | `state=\"ACTIVE\" AND findingClass=\"THREAT\"` |\n| **Observations**              | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"OBSERVATION\"`                :\n| **Sensitive Data Risks**      | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"SENSITIVE_DATA_RISK\"`        :\n| **Chokepoints**               | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"CHOKEPOINT\"`                 :\n| **Posture Violations**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"POSTURE_VIOLATION\"`          :\n| **Secrets**                   | `state=\"ACTIVE\" AND findingClass=\"SECRET\"` |\n| **SCC Errors**                | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"SCC_ERROR\"`                  :\n| **Specific Category**         | `state=\"ACTIVE\" AND category=\"{category}\"` |\n\n### 3. Discovery & Aggregation (Grouping)\n\n**Intent**: User wants high-level counts or landscape overview (e.g., \"What are\nthe most common findings?\", \"Show me a summary by category\"). \\\n**Action**: Use `gcloud scc findings group`. Specify `--location={location}`\n(default `global` unless querying a specific region). Allowed fields for\n`--group-by` are strictly: `resource_name`, `category`, `state`, `parent`.\n\n```bash\ngcloud scc findings group {parent} \\\n  --location={location} \\\n  --group-by=\"{group_by_field}\" \\\n  --filter=\"state=\\\"ACTIVE\\\"\" \\\n  --format=\"json\"\n```\n\n--------------------------------------------------------------------------------\n\n## Payload Analysis & Handoff\n\nOnce the finding JSON payload is retrieved:\n\n*   **For `TOXIC_COMBINATION` Findings**:\n    1.  Verify the `attackExposure` field is present and has a `score > 0`.\n    2.  Inspect the attack path nodes, edges, or referenced\n        `attackExposureResult` to identify exposed resources and attack\n        trajectories.\n*   **For `VULNERABILITY` Findings**:\n    1.  Extract CVSS scores, exploit signals (`exploitationActivity`,\n        `observedInTheWild`, `zeroDay`), upstream fix status\n        (`upstreamFixAvailable`), and affected package details from the\n        `vulnerability` object to evaluate risk:\n        -   `vulnerability.cve.id`\n        -   `vulnerability.cve.cvssv3.baseScore`\n        -   `vulnerability.cve.cvssv3.attackVector`\n        -   `vulnerability.cve.exploitationActivity`\n        -   `vulnerability.cve.observedInTheWild`\n        -   `vulnerability.cve.zeroDay`\n        -   `vulnerability.cve.upstreamFixAvailable`\n        -   `vulnerability.offendingPackage.packageName`\n        -   `vulnerability.offendingPackage.packageVersion`\n        -   `vulnerability.fixedPackage.packageVersion`\n        -   `vulnerability.securityBulletin.suggestedUpgradeVersion`\n*   **Handoff**: Do not draft remediation plans, patch resources, or execute\n    configuration commands. Pass the extracted finding payload to the\n    appropriate remediation or IAM analyzer skill to manage the remediation\n    action loop.\n\n--------------------------------------------------------------------------------\n\n## Reference Schema\n\nSee [finding_schema.md](references\u002Ffinding_schema.md) for the JSON structure of\na Security Command Center finding.\n","# Security Command Center Query Skill on Google Cloud\n\nProvides guidelines and read-only `gcloud` CLI command patterns for querying and\nretrieving security findings, external exposures, toxic combinations,\nvulnerabilities, threats, and sensitive data risks from Security Command Center\non Google Cloud.\n\n> [!IMPORTANT] There is NO `gcloud scc findings describe` command (`Invalid\n> choice: 'describe'`). To retrieve details for a specific finding by its name,\n> always use `gcloud scc findings list` with a filter on `name`.\n\n## Usage Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n--------------------------------------------------------------------------------\n\n## Core Execution Rules\n\n1.  **Read-Only & Zero-Speculation (Parent Scope Required)**: Keep all\n    executions strictly read-only. Every `gcloud scc findings list` or `group`\n    command strictly requires an explicit `{parent}` scope\n    (`organizations\u002F{id}`, `projects\u002F{id}`, or `folders\u002F{id}`). If the parent\n    scope is missing from the prompt and cannot be inferred from a full finding\n    name, **DO NOT run any `gcloud` commands** (do not execute queries without\n    parent, and never inspect `gcloud config`). Halt immediately before\n    executing commands and ask the user for the parent resource scope.\n2.  **Bounded Execution & No Runaway Loops**:\n    -   Limit tool calls to what is strictly necessary to complete the query\n        (typically 1 call for direct queries, or 2 calls for List → Deep Dive\n        workflows).\n    -   If a command fails due to permission\u002Fauth errors, or if a specific\n        finding query returns `[]`, halt immediately. Do not attempt blind\n        brute-force retries with different flags, and never search the local\n        workspace for credentials.\n3.  **Immediate Halt on Errors**: If any command fails with `PERMISSION_DENIED`,\n    `IAM_PERMISSION_DENIED`, credential expiration, or network timeouts, halt\n    immediately and report the verbatim error message. Do not search the\n    workspace for credentials or run diagnostic loops.\n4.  **Ambiguous or Multiple Findings**: If multiple finding names are provided\n    when a single finding report is requested, or if listing returns multiple\n    findings, do not investigate all of them or unilaterally pick one. Halt\n    immediately without running queries and ask the user to clarify which\n    specific finding name they want details for. If zero findings are returned\n    from a query, report that no active findings exist and halt immediately.\n5.  **Do Not Query Attack Path Resources**: Analyze only the data present in the\n    Security Command Center finding JSON payload. Do not run commands to\n    describe, verify, or query underlying Google Cloud resources (such as VMs,\n    Cloud Storage buckets, service accounts, or IAM policies).\n6.  **Parent Scope Resolution**:\n    -   For listing and grouping, format the parent resource path as\n        `organizations\u002F{org_id}`, `projects\u002F{project_id}`, or\n        `folders\u002F{folder_id}`.\n    -   For deep dive queries on a specific finding name, extract the `{parent}`\n        resource prefix before `\u002Fsources\u002F...`:\n        -   `organizations\u002F{org_id}\u002Fsources\u002F...` → `{parent}` is\n            `organizations\u002F{org_id}`\n        -   `folders\u002F{folder_id}\u002Fsources\u002F...` → `{parent}` is\n            `folders\u002F{folder_id}`\n        -   `projects\u002F{project_id}\u002Fsources\u002F...` → `{parent}` is\n            `projects\u002F{project_id}` Extract the parent prefix regardless of\n            whether the finding resource name is global (4-segment) or\n            location-qualified (5-segment with `\u002Flocations\u002F{location}\u002F`).\n            Execute the deep dive query using the extracted `{parent}`. Do not\n            reject or halt on project- or folder-level findings.\n\n--------------------------------------------------------------------------------\n\n## Data Residency & Regional Endpoints\n\nWhen Data Residency (DRZ) is enabled, findings are stored and accessible only\nwithin their designated regional location (`us`, `eu`, or `me-central2`).\nQueries across different locations do not return findings from other regions.\n\n### 1. Location Parameterization\n\nAll `gcloud scc findings` commands require specifying the target location via\n`--location={location}`:\n\n-   **Default**: `global` (used when data residency is not enabled or for global\n    findings).\n-   **Supported Regional Locations**:\n    -   `us` (United States multi-region)\n    -   `eu` (European Union multi-region)\n    -   `me-central2` (Kingdom of Saudi Arabia regional location)\n\n### 2. API Endpoint Overrides\n\nWhen data residency (DRZ) is enabled for an organization in a regional location\n(`us`, `eu`, or `me-central2`), configure the regional API endpoint override\nbefore executing finding queries:\n\n```bash\ngcloud config set api_endpoint_overrides\u002Fsecuritycenter https:\u002F\u002Fsecuritycenter.{LOCATION}.rep.googleapis.com\u002F\n```\n\nExample for the European Union (`eu`) region:\n\n```bash\ngcloud config set api_endpoint_overrides\u002Fsecuritycenter https:\u002F\u002Fsecuritycenter.eu.rep.googleapis.com\u002F\n```\n\nTo reset the endpoint back to default global routing:\n\n```bash\ngcloud config unset api_endpoint_overrides\u002Fsecuritycenter\n```\n\n### 3. Location-Qualified Finding Resource Names\n\nRegional finding resource names include the `\u002Flocations\u002F{location}\u002F` path\nsegment:\n\n-   Organization-level:\n    `organizations\u002F{org_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n-   Folder-level:\n    `folders\u002F{folder_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n-   Project-level:\n    `projects\u002F{project_id}\u002Fsources\u002F{source_id}\u002Flocations\u002F{location}\u002Ffindings\u002F{finding_id}`\n\nWhen performing a Deep Dive on a location-qualified finding name:\n\n1.  Extract the `{parent}` scope (the prefix before `\u002Fsources\u002F...`, e.g.,\n    `organizations\u002F{org_id}`).\n2.  Extract the `{location}` from `\u002Flocations\u002F{location}\u002F` (e.g., `eu`, `us`,\n    `me-central2`). If not present in the finding name, default to `global` (or\n    the user-specified location).\n3.  Execute the query with `--location={location}` and\n    `--filter=\"name=\\\"{finding_name}\\\"\"`.\n\n--------------------------------------------------------------------------------\n\n## Intent-Based Query Strategies\n\n### 1. Deep Dive (Specific Finding Details)\n\n**Intent**: User provides a specific finding name or explicitly asks to retrieve\nall details for one finding. \\\n**Action**: Execute `gcloud scc findings list` with a strict filter on `name`\nand NO `--field-mask` to retrieve the complete JSON payload. Specify\n`--location={location}` (default `global` unless a regional location is\nindicated or present in the finding name).\n\n```bash\ngcloud scc findings list {parent} \\\n  --location={location} \\\n  --filter=\"name=\\\"{finding_name}\\\"\" \\\n  --format=\"json\" --limit=1\n```\n\n### 2. Listing (Filtered Projection)\n\n**Intent**: User wants to list active findings matching criteria without pulling\nfull nested payloads. \\\n**Action**: Use `--field-mask` projection to restrict output size. Specify\n`--location={location}` (default `global` unless querying a specific region).\n\n```bash\ngcloud scc findings list {parent} \\\n  --location={location} \\\n  --filter=\"{filter_expression}\" \\\n  --field-mask=\"finding.name,finding.parentDisplayName,finding.findingClass,finding.category,finding.state,finding.eventTime,finding.severity,finding.resourceName\" \\\n  --format=\"json\" --order-by=\"severity,event_time desc\" --limit=100\n```\n\n| Intent \u002F Target Finding Class | `--filter` Expression                      |\n| :---------------------------- | :----------------------------------------- |\n| **All Active Findings**       | `state=\"ACTIVE\"`                           |\n| **Vulnerabilities**           | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"VULNERABILITY\"`              :\n| **Misconfigurations**         | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"MISCONFIGURATION\"`           :\n| **Toxic Combinations**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"TOXIC_COMBINATION\"`          :\n| **External Exposures**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"EXTERNAL_EXPOSURE\"`          :\n| **Threats**                   | `state=\"ACTIVE\" AND findingClass=\"THREAT\"` |\n| **Observations**              | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"OBSERVATION\"`                :\n| **Sensitive Data Risks**      | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"SENSITIVE_DATA_RISK\"`        :\n| **Chokepoints**               | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"CHOKEPOINT\"`                 :\n| **Posture Violations**        | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"POSTURE_VIOLATION\"`          :\n| **Secrets**                   | `state=\"ACTIVE\" AND findingClass=\"SECRET\"` |\n| **SCC Errors**                | `state=\"ACTIVE\" AND                        |\n:                               : findingClass=\"SCC_ERROR\"`                  :\n| **Specific Category**         | `state=\"ACTIVE\" AND category=\"{category}\"` |\n\n### 3. Discovery & Aggregation (Grouping)\n\n**Intent**: User wants high-level counts or landscape overview (e.g., \"What are\nthe most common findings?\", \"Show me a summary by category\"). \\\n**Action**: Use `gcloud scc findings group`. Specify `--location={location}`\n(default `global` unless querying a specific region). Allowed fields for\n`--group-by` are strictly: `resource_name`, `category`, `state`, `parent`.\n\n```bash\ngcloud scc findings group {parent} \\\n  --location={location} \\\n  --group-by=\"{group_by_field}\" \\\n  --filter=\"state=\\\"ACTIVE\\\"\" \\\n  --format=\"json\"\n```\n\n--------------------------------------------------------------------------------\n\n## Payload Analysis & Handoff\n\nOnce the finding JSON payload is retrieved:\n\n*   **For `TOXIC_COMBINATION` Findings**:\n    1.  Verify the `attackExposure` field is present and has a `score > 0`.\n    2.  Inspect the attack path nodes, edges, or referenced\n        `attackExposureResult` to identify exposed resources and attack\n        trajectories.\n*   **For `VULNERABILITY` Findings**:\n    1.  Extract CVSS scores, exploit signals (`exploitationActivity`,\n        `observedInTheWild`, `zeroDay`), upstream fix status\n        (`upstreamFixAvailable`), and affected package details from the\n        `vulnerability` object to evaluate risk:\n        -   `vulnerability.cve.id`\n        -   `vulnerability.cve.cvssv3.baseScore`\n        -   `vulnerability.cve.cvssv3.attackVector`\n        -   `vulnerability.cve.exploitationActivity`\n        -   `vulnerability.cve.observedInTheWild`\n        -   `vulnerability.cve.zeroDay`\n        -   `vulnerability.cve.upstreamFixAvailable`\n        -   `vulnerability.offendingPackage.packageName`\n        -   `vulnerability.offendingPackage.packageVersion`\n        -   `vulnerability.fixedPackage.packageVersion`\n        -   `vulnerability.securityBulletin.suggestedUpgradeVersion`\n*   **Handoff**: Do not draft remediation plans, patch resources, or execute\n    configuration commands. Pass the extracted finding payload to the\n    appropriate remediation or IAM analyzer skill to manage the remediation\n    action loop.\n\n--------------------------------------------------------------------------------\n\n## Reference Schema\n\nSee [finding_schema.md](references\u002Ffinding_schema.md) for the JSON structure of\na Security Command Center finding.\n",{"name":5,"metadata":25,"description":7},{"version":26,"category":27},"1.0.2","Security","main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-query",{"tool":43,"command":44},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-query",{"tool":46,"command":47},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill google-cloud-scc-query","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002FSKILL.md",true,[51,57,61,65],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"INSTALL-SOURCE.json","REFERENCE","参考文档",526,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002FINSTALL-SOURCE.json",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",11358,{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fattribution.md",1914,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002Freferences\u002Fattribution.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ffinding_schema.md",3912,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgoogle-cloud-scc-query\u002Freferences\u002Ffinding_schema.md",[70,78,87,95,103,111],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\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":82,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]