Back to catalog
Static reviewDevelopment

Skill dossier

implementing-cloud-dlp-for-data-protection

Source declaration

Implement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data (PII, PHI, financial data) across cloud storage, databases, and pipelines. Use for GDPR/HIPAA/PCI DSS data-discovery, cloud data governance, or CI/CD DLP scanning; not for endpoint, email, or network-level DLP.

The author's original description, preserved in English. It describes intent, not verified performance.

Implement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data (PII, PHI, financial data) across cloud storage, databases, and pipelines. Use for GDPR/HIPAA/PCI DSS data-discovery, cloud data governance, or CI/CD DLP scanning; not for endpoint, email, or network-level DLP.

developmentreferencesscripts

Research summary

Machine-generated analysis; pending human review

These observations come from deterministic source parsing, not a human security review or controlled task evaluation.

Implement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data (PII, PHI, financial data) across cloud storage, databases, and pipelines. Use for GDPR/HIPAA/PCI DSS data-discovery, cloud data governance, or CI/CD DLP scanning; not for endpoint, email, or network-level DLP. This bilingual summary is generated deterministically from collected source text and file structure; it is pending human editorial review.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Workflow [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L65]
  • Step 1: Deploy Amazon Macie for S3 Data Discovery [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L67]
  • Step 2: Configure Google Cloud DLP API for Data Inspection [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L116]
  • Step 3: Implement Data De-identification with Cloud DLP [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L173]
  • Step 4: Configure Azure Information Protection [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L248]
  • Step 5: Integrate DLP into Data Pipelines [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L296]
  • Step 6: Monitor DLP Findings and Generate Reports [Source statement; provisional, not tested. Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L361]

Limitations & scope

  • Static analysis cannot assess runtime behavior, command success, network reachability, or model output quality.
  • No commands, scripts, network requests, model calls, or controlled skill executions were performed.
  • Category, tags, capabilities, workflows, and bilingual editorial summaries are deterministic candidates pending human review, not verified outcomes.
  • Exact token counts are unavailable until a later pipeline performs and records an official model-specific count.

Relevant for

  • Practitioners evaluating whether to inspect and install the source skill; this audience is inferred from the product context, not measured usage. [Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L1-L43]

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
4
Markdown files
2
scripts
1
references
1
Size
36.5 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/implementing-cloud-dlp-for-data-protection/LICENSEOther11 KB
skills/implementing-cloud-dlp-for-data-protection/references/api-reference.mdReference2.1 KB
skills/implementing-cloud-dlp-for-data-protection/scripts/agent.pyScript7.2 KB
skills/implementing-cloud-dlp-for-data-protection/SKILL.mdInstruction16.2 KB

SKILL.md frontmatter

{
  "name": "implementing-cloud-dlp-for-data-protection",
  "description": "Implement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data (PII, PHI, financial data) across cloud storage, databases, and pipelines. Use for GDPR/HIPAA/PCI DSS data-discovery, cloud data governance, or CI/CD DLP scanning; not for endpoint, email, or network-level DLP.\n",
  "domain": "cybersecurity",
  "subdomain": "cloud-security",
  "tags": [
    "cloud-security",
    "dlp",
    "data-protection",
    "macie",
    "data-classification",
    "privacy"
  ],
  "version": "1.0",
  "author": "mahipal",
  "license": "Apache-2.0",
  "nist_ai_rmf": [
    "MEASURE-2.7",
    "MAP-5.1",
    "MANAGE-2.4",
    "MEASURE-2.8",
    "MEASURE-2.9"
  ],
  "atlas_techniques": [
    "AML.T0070",
    "AML.T0066",
    "AML.T0082"
  ],
  "nist_csf": [
    "PR.IR-01",
    "ID.AM-08",
    "GV.SC-06",
    "DE.CM-01"
  ],
  "mitre_attack": [
    "T1078.004",
    "T1530",
    "T1537",
    "T1580"
  ]
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Decision

    When to Use

    Source-described decision candidate under “When to Use”; not verified execution.

  2. 02
    Action

    Workflow

    Source-described action candidate under “Workflow”; not verified execution.

  3. 03
    Action

    Step 1: Deploy Amazon Macie for S3 Data Discovery

    Source-described action candidate under “Step 1: Deploy Amazon Macie for S3 Data Discovery”; not verified execution.

  4. 04
    Action

    Step 2: Configure Google Cloud DLP API for Data Inspection

    Source-described action candidate under “Step 2: Configure Google Cloud DLP API for Data Inspection”; not verified execution.

  5. 05
    Action

    Use Google Cloud DLP to inspect and de-identify sensitive data across GCP resources.

    Source-described action candidate under “Step 2: Configure Google Cloud DLP API for Data Inspection”; not verified execution.

  6. 06
    Action

    Step 3: Implement Data De-identification with Cloud DLP

    Source-described action candidate under “Step 3: Implement Data De-identification with Cloud DLP”; not verified execution.

Inspect all extracted workflow candidates (20 candidate steps)
  1. 07
    Action

    Step 4: Configure Azure Information Protection

    Source-described action candidate under “Step 4: Configure Azure Information Protection”; not verified execution.

  2. 08
    Action

    Step 5: Integrate DLP into Data Pipelines

    Source-described action candidate under “Step 5: Integrate DLP into Data Pipelines”; not verified execution.

  3. 09
    Action

    Step 6: Monitor DLP Findings and Generate Reports

    Source-described action candidate under “Step 6: Monitor DLP Findings and Generate Reports”; not verified execution.

  4. 10
    Action

    Key Concepts

    Source-described action candidate under “Key Concepts”; not verified execution.

  5. 11
    Action

    Tools & Systems

    Source-described action candidate under “Tools & Systems”; not verified execution.

  6. 12
    Action

    Common Scenarios

    Source-described action candidate under “Common Scenarios”; not verified execution.

  7. 13
    Action

    Enable Macie and create a one-time classification job against the data lake bucket

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  8. 14
    Action

    Review Macie findings to identify which objects contain PII and what types

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  9. 15
    Action

    Create custom data identifiers for organization-specific formats (employee IDs, account numbers)

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  10. 16
    Action

    Implement a weekly scheduled Macie job for ongoing discovery

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  11. 17
    Action

    Build a data pipeline gate that scans new data before promotion to the data lake

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  12. 18
    Action

    Apply de-identification transforms (masking SSNs, tokenizing emails) for analytics use cases

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  13. 19
    Action

    Configure S3 bucket policies to restrict access to classified data to authorized roles only

    Source-described action candidate under “Scenario: Discovering PII in an Unprotected S3 Data Lake”; not verified execution.

  14. 20
    Output

    Output Format

    Source-described output candidate under “Output Format”; not verified execution.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Items warrant review

11 deterministic lexical finding(s) require review across the collected text. Findings can occur in documentation and do not prove execution or exploitability; binary-only files were not scanned.

Network accessObserved
File writesObserved
Credential useNot observed
Medium

Network access is mentioned

8 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 8 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Note

File modification is described or implemented

3 occurrences

This line contains a possible file-write or redirection operation. Check destination paths and overwrite behavior; the static review did not write any file. This rule matched 3 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
Inspect the pinned source at https://github.com/mukul975/Anthropic-Cybersecurity-Skills/blob/54a798831d2266a3ca61ce68a7acb80b81160d57/skills/implementing-cloud-dlp-for-data-protection/SKILL.md and follow the source repository's installation instructions. No installation was performed or verified by this static analyzer. Source license: Apache-2.0.

Prerequisites

  • Static analysis cannot assess runtime behavior, command success, network reachability, or model output quality.
  • No commands, scripts, network requests, model calls, or controlled skill executions were performed.
  • Category, tags, capabilities, workflows, and bilingual editorial summaries are deterministic candidates pending human review, not verified outcomes.
  • Exact token counts are unavailable until a later pipeline performs and records an official model-specific count.

Example prompts

Not provided

A decision, with its limits attached

Strengths

  • The snapshot contains 4 collected file(s), 2 Markdown file(s), and 1 script file(s), enabling source-level inspection. [Evidence: skills/implementing-cloud-dlp-for-data-protection/SKILL.md:L1]

Considerations

  • No functional, security, or model-quality result has been established. Human review must inspect source context and all cited findings before installation or publication.
Research conclusion

Provisional deterministic static inventory only; pending human editorial review and, separately, controlled evaluation. No install recommendation, security assurance, or effectiveness claim is made.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

mukul975Anthropic-Cybersecurity-Skillsskills/implementing-cloud-dlp-for-data-protection
Source type
Community
Commit
54a798831d2266a3ca61ce68a7acb80b81160d57
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
Apache-2.0
Repository stars
36,446
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.