Back to catalog
Static reviewDevelopment

Skill dossier

performing-cloud-native-threat-hunting-with-aws-detective

Source declaration

Investigate AWS security incidents using Amazon Detective's behavior graphs, built from CloudTrail, VPC Flow Logs, GuardDuty, and EKS audit logs, to trace entity timelines and profile IAM users, roles, EC2 instances, and IP addresses for lateral movement. Use when triaging GuardDuty findings, investigating a suspected AWS compromise, or reconstructing an attacker's activity timeline across AWS accounts.

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

Investigate AWS security incidents using Amazon Detective's behavior graphs, built from CloudTrail, VPC Flow Logs, GuardDuty, and EKS audit logs, to trace entity timelines and profile IAM users, roles, EC2 instances, and IP addresses for lateral movement. Use when triaging GuardDuty findings, investigating a suspected AWS compromise, or reconstructing an attacker's activity timeline across AWS accounts.

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.

Investigate AWS security incidents using Amazon Detective's behavior graphs, built from CloudTrail, VPC Flow Logs, GuardDuty, and EKS audit logs, to trace entity timelines and profile IAM users, roles, EC2 instances, and IP addresses for lateral movement. Use when triaging GuardDuty findings, investigating a suspected AWS compromise, or reconstructing an attacker's activity timeline across AWS accounts. 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

  • Steps [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L59]
  • Step 1: List Available Behavior Graphs [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L61]
  • Step 2: Investigate a Suspicious IAM User [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L67]
  • Step 3: Search Entities Programmatically [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L76]
  • Step 4: Analyze Finding Groups for Attack Campaigns [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L127]
  • Step 5: Check Entity Indicators [Source statement; provisional, not tested. Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L137]

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/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.md:L1-L34]

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
6
Markdown files
5
scripts
1
references
4
Size
24.4 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/performing-cloud-native-threat-hunting-with-aws-detective/assets/template.mdReference1.1 KB
skills/performing-cloud-native-threat-hunting-with-aws-detective/references/api-reference.mdReference8.5 KB
skills/performing-cloud-native-threat-hunting-with-aws-detective/references/standards.mdReference1.1 KB
skills/performing-cloud-native-threat-hunting-with-aws-detective/references/workflows.mdReference1.1 KB
skills/performing-cloud-native-threat-hunting-with-aws-detective/scripts/process.pyScript6.9 KB
skills/performing-cloud-native-threat-hunting-with-aws-detective/SKILL.mdInstruction5.8 KB

SKILL.md frontmatter

{
  "name": "performing-cloud-native-threat-hunting-with-aws-detective",
  "description": "Investigate AWS security incidents using Amazon Detective's behavior graphs, built from CloudTrail, VPC Flow Logs, GuardDuty, and EKS audit logs, to trace entity timelines and profile IAM users, roles, EC2 instances, and IP addresses for lateral movement. Use when triaging GuardDuty findings, investigating a suspected AWS compromise, or reconstructing an attacker's activity timeline across AWS accounts.",
  "domain": "cybersecurity",
  "subdomain": "cloud-security",
  "tags": [
    "aws-detective",
    "threat-hunting",
    "cloud-security",
    "guardduty",
    "behavior-graph",
    "aws",
    "iam",
    "ec2",
    "incident-investigation"
  ],
  "version": "1.0",
  "author": "juliosuas",
  "license": "Apache-2.0",
  "nist_csf": [
    "PR.IR-01",
    "ID.AM-08",
    "GV.SC-06",
    "DE.CM-01"
  ],
  "mitre_attack": [
    "T1078.004",
    "T1530",
    "T1537",
    "T1580",
    "T1071"
  ]
}

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
    Action

    Overview

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

  2. 02
    Action

    Key Concepts

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

  3. 03
    Action

    Steps

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

  4. 04
    Action

    Step 1: List Available Behavior Graphs

    Source-described action candidate under “Step 1: List Available Behavior Graphs”; not verified execution.

  5. 05
    Action

    Step 2: Investigate a Suspicious IAM User

    Source-described action candidate under “Step 2: Investigate a Suspicious IAM User”; not verified execution.

  6. 06
    Action

    Step 3: Search Entities Programmatically

    Source-described action candidate under “Step 3: Search Entities Programmatically”; not verified execution.

Inspect all extracted workflow candidates (15 candidate steps)
  1. 07
    Action

    Step 4: Analyze Finding Groups for Attack Campaigns

    Source-described action candidate under “Step 4: Analyze Finding Groups for Attack Campaigns”; not verified execution.

  2. 08
    Action

    Step 5: Check Entity Indicators

    Source-described action candidate under “Step 5: Check Entity Indicators”; not verified execution.

  3. 09
    Output

    Expected Output

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

  4. 10
    Action

    Verification

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

  5. 11
    Action

    Confirm behavior graph has data: `aws detective list-graphs` returns non-empty list

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

  6. 12
    Action

    Validate investigation results contain entity timelines with API call sequences

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

  7. 13
    Action

    Cross-reference Detective findings with raw CloudTrail logs for accuracy

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

  8. 14
    Action

    Verify finding group correlations match manual investigation conclusions

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

  9. 15
    Action

    Confirm automated alerts trigger for HIGH/CRITICAL severity investigations

    Source-described action candidate under “Verification”; 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

13 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
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.

Medium

Network access is mentioned

10 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 10 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/performing-cloud-native-threat-hunting-with-aws-detective/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 6 collected file(s), 5 Markdown file(s), and 1 script file(s), enabling source-level inspection. [Evidence: skills/performing-cloud-native-threat-hunting-with-aws-detective/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/performing-cloud-native-threat-hunting-with-aws-detective
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.