Back to catalog
Static reviewDevelopment

Skill dossier

detecting-business-email-compromise

Source declaration

Detect Business Email Compromise (BEC) fraud, where attackers impersonate executives or vendors to trick employees into wire transfers or data disclosure without malicious links, using email gateway rules, behavioral analytics, and financial process controls. Use when investigating a suspected executive/vendor impersonation email or building detection rules for social-engineering fund-transfer fraud.

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

Detect Business Email Compromise (BEC) fraud, where attackers impersonate executives or vendors to trick employees into wire transfers or data disclosure without malicious links, using email gateway rules, behavioral analytics, and financial process controls. Use when investigating a suspected executive/vendor impersonation email or building detection rules for social-engineering fund-transfer fraud.

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.

Detect Business Email Compromise (BEC) fraud, where attackers impersonate executives or vendors to trick employees into wire transfers or data disclosure without malicious links, using email gateway rules, behavioral analytics, and financial process controls. Use when investigating a suspected executive/vendor impersonation email or building detection rules for social-engineering fund-transfer fraud. 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/detecting-business-email-compromise/SKILL.md:L114]
  • Step 1: Configure BEC-Specific Email Rules [Source statement; provisional, not tested. Evidence: skills/detecting-business-email-compromise/SKILL.md:L116]
  • Step 2: Deploy Behavioral Analytics [Source statement; provisional, not tested. Evidence: skills/detecting-business-email-compromise/SKILL.md:L122]
  • Step 3: Implement Financial Controls [Source statement; provisional, not tested. Evidence: skills/detecting-business-email-compromise/SKILL.md:L127]
  • Step 4: Monitor for Account Compromise [Source statement; provisional, not tested. Evidence: skills/detecting-business-email-compromise/SKILL.md:L133]

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/detecting-business-email-compromise/SKILL.md:L1-L76]

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
8
Markdown files
5
scripts
2
references
4
Size
39.9 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/detecting-business-email-compromise/assets/template.mdReference1.1 KB
skills/detecting-business-email-compromise/LICENSEOther11 KB
skills/detecting-business-email-compromise/references/api-reference.mdReference1.9 KB
skills/detecting-business-email-compromise/references/standards.mdReference1.4 KB
skills/detecting-business-email-compromise/references/workflows.mdReference2.3 KB
skills/detecting-business-email-compromise/scripts/agent.pyScript5.5 KB
skills/detecting-business-email-compromise/scripts/process.pyScript11.7 KB
skills/detecting-business-email-compromise/SKILL.mdInstruction5 KB

SKILL.md frontmatter

{
  "name": "detecting-business-email-compromise",
  "description": "Detect Business Email Compromise (BEC) fraud, where attackers impersonate executives or vendors to trick employees into wire transfers or data disclosure without malicious links, using email gateway rules, behavioral analytics, and financial process controls. Use when investigating a suspected executive/vendor impersonation email or building detection rules for social-engineering fund-transfer fraud.",
  "domain": "cybersecurity",
  "subdomain": "phishing-defense",
  "tags": [
    "phishing",
    "email-security",
    "social-engineering",
    "dmarc",
    "awareness",
    "bec",
    "fraud"
  ],
  "version": "1.0",
  "author": "mahipal",
  "license": "Apache-2.0",
  "atlas_techniques": [
    "AML.T0052",
    "AML.T0088"
  ],
  "nist_ai_rmf": [
    "GOVERN-6.2",
    "MAP-5.2"
  ],
  "d3fend_techniques": [
    "Restore Object",
    "Restore Configuration",
    "Application Configuration Hardening",
    "Application Hardening",
    "Disable Remote Access"
  ],
  "nist_csf": [
    "PR.AT-01",
    "DE.CM-09",
    "RS.CO-02",
    "DE.AE-02"
  ],
  "mitre_attack": [
    "T1566.002",
    "T1534",
    "T1114.002",
    "T1657",
    "T1078.004"
  ],
  "mitre_f3": {
    "version": "1.1",
    "tactics": [
      "initial-access",
      "positioning",
      "monetization",
      "stealth"
    ],
    "techniques": [
      {
        "id": "T1672",
        "name": "Email Spoofing",
        "tactic": "stealth",
        "source": "attack"
      },
      {
        "id": "F1032",
        "name": "Impersonate Official",
        "tactic": "initial-access",
        "source": "f3"
      },
      {
        "id": "F1036",
        "name": "New Vendor Setup",
        "tactic": "positioning",
        "source": "f3"
      },
      {
        "id": "F1005.006",
        "name": "Account Manipulation: Change of Payment Details",
        "tactic": "positioning",
        "source": "f3"
      },
      {
        "id": "F1025.003",
        "name": "Electronic Funds Transfer: Wire Transfer",
        "tactic": "monetization",
        "source": "f3"
      },
      {
        "id": "F1022",
        "name": "Delete Relevant Emails",
        "tactic": "stealth",
        "source": "f3"
      }
    ]
  }
}

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
    Decision

    When to Use

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

  3. 03
    Action

    Key Concepts

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

  4. 04
    Action

    CEO Fraud: Attacker impersonates CEO, requests urgent wire transfer

    Source-described action candidate under “BEC Attack Types (FBI IC3 Classification)”; not verified execution.

  5. 05
    Action

    Account Compromise: Employee email compromised, used to request payments from vendors

    Source-described action candidate under “BEC Attack Types (FBI IC3 Classification)”; not verified execution.

  6. 06
    Action

    False Invoice Scheme: Fake invoices from "vendor" with changed bank details

    Source-described action candidate under “BEC Attack Types (FBI IC3 Classification)”; not verified execution.

Inspect all extracted workflow candidates (30 candidate steps)
  1. 07
    Action

    Attorney Impersonation: Impersonates legal counsel for urgent confidential transfers

    Source-described action candidate under “BEC Attack Types (FBI IC3 Classification)”; not verified execution.

  2. 08
    Action

    Data Theft: Requests W-2, tax forms, or PII from HR

    Source-described action candidate under “BEC Attack Types (FBI IC3 Classification)”; not verified execution.

  3. 09
    Action

    Workflow

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

  4. 10
    Action

    Step 1: Configure BEC-Specific Email Rules

    Source-described action candidate under “Step 1: Configure BEC-Specific Email Rules”; not verified execution.

  5. 11
    Output

    Flag emails with VIP display names from external domains

    Source-described output candidate under “Step 1: Configure BEC-Specific Email Rules”; not verified execution.

  6. 12
    Action

    Detect financial keywords combined with urgency language

    Source-described action candidate under “Step 1: Configure BEC-Specific Email Rules”; not verified execution.

  7. 13
    Action

    Alert on first-time sender to finance/accounting staff

    Source-described action candidate under “Step 1: Configure BEC-Specific Email Rules”; not verified execution.

  8. 14
    Action

    Check for Reply-To domain mismatch

    Source-described action candidate under “Step 1: Configure BEC-Specific Email Rules”; not verified execution.

  9. 15
    Action

    Step 2: Deploy Behavioral Analytics

    Source-described action candidate under “Step 2: Deploy Behavioral Analytics”; not verified execution.

  10. 16
    Action

    Baseline normal communication patterns per user

    Source-described action candidate under “Step 2: Deploy Behavioral Analytics”; not verified execution.

  11. 17
    Action

    Detect anomalous requests (unusual recipient, unusual time, unusual request type)

    Source-described action candidate under “Step 2: Deploy Behavioral Analytics”; not verified execution.

  12. 18
    Action

    Monitor for email forwarding rule changes (T1114.003)

    Source-described action candidate under “Step 2: Deploy Behavioral Analytics”; not verified execution.

  13. 19
    Action

    Step 3: Implement Financial Controls

    Source-described action candidate under “Step 3: Implement Financial Controls”; not verified execution.

  14. 20
    Action

    Dual-authorization for wire transfers above threshold

    Source-described action candidate under “Step 3: Implement Financial Controls”; not verified execution.

  15. 21
    Action

    Out-of-band verification for payment detail changes (phone callback)

    Source-described action candidate under “Step 3: Implement Financial Controls”; not verified execution.

  16. 22
    Action

    Vendor payment change verification process

    Source-described action candidate under “Step 3: Implement Financial Controls”; not verified execution.

  17. 23
    Action

    Finance team training on BEC red flags

    Source-described action candidate under “Step 3: Implement Financial Controls”; not verified execution.

  18. 24
    Action

    Step 4: Monitor for Account Compromise

    Source-described action candidate under “Step 4: Monitor for Account Compromise”; not verified execution.

  19. 25
    Action

    Detect impossible travel in email login locations

    Source-described action candidate under “Step 4: Monitor for Account Compromise”; not verified execution.

  20. 26
    Action

    Alert on email forwarding rule creation

    Source-described action candidate under “Step 4: Monitor for Account Compromise”; not verified execution.

  21. 27
    Action

    Monitor for mailbox delegation changes

    Source-described action candidate under “Step 4: Monitor for Account Compromise”; not verified execution.

  22. 28
    Action

    Check for inbox rules hiding BEC-related emails

    Source-described action candidate under “Step 4: Monitor for Account Compromise”; not verified execution.

  23. 29
    Action

    Tools & Resources

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

  24. 30
    Action

    Validation

    Source-described action candidate under “Validation”; 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

23 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

19 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 19 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

4 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 4 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/detecting-business-email-compromise/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 8 collected file(s), 5 Markdown file(s), and 2 script file(s), enabling source-level inspection. [Evidence: skills/detecting-business-email-compromise/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/detecting-business-email-compromise
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.