Back to catalog
Static reviewDevelopment

Skill dossier

detecting-deepfake-audio-in-vishing-attacks

Source declaration

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models, supporting batch audio analysis, confidence scoring, and forensic reporting. Use for deepfake voice detection, vishing investigations, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.

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

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models, supporting batch audio analysis, confidence scoring, and forensic reporting. Use for deepfake voice detection, vishing investigations, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.

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 AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models, supporting batch audio analysis, confidence scoring, and forensic reporting. Use for deepfake voice detection, vishing investigations, AI-generated speech analysis, voice cloning detection, or audio authenticity verification. 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-deepfake-audio-in-vishing-attacks/SKILL.md:L93]
  • Step 1: Audio Preprocessing [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L95]
  • Step 2: Extract Spectral Features [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L115]
  • Step 3: Build Feature Vector and Classify [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L144]
  • Step 4: Temporal Artifact Analysis [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L171]
  • Step 5: Spectrogram Visual Inspection [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L185]
  • Step 6: Generate Forensic Report [Source statement; provisional, not tested. Evidence: skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.md:L203]

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-deepfake-audio-in-vishing-attacks/SKILL.md:L1-L71]

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
51.5 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/detecting-deepfake-audio-in-vishing-attacks/LICENSEOther11 KB
skills/detecting-deepfake-audio-in-vishing-attacks/references/api-reference.mdReference5.3 KB
skills/detecting-deepfake-audio-in-vishing-attacks/scripts/agent.pyScript24.1 KB
skills/detecting-deepfake-audio-in-vishing-attacks/SKILL.mdInstruction11.1 KB

SKILL.md frontmatter

{
  "name": "detecting-deepfake-audio-in-vishing-attacks",
  "description": "Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models, supporting batch audio analysis, confidence scoring, and forensic reporting. Use for deepfake voice detection, vishing investigations, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.",
  "domain": "cybersecurity",
  "subdomain": "social-engineering-defense",
  "tags": [
    "deepfake-detection",
    "vishing",
    "audio-forensics",
    "MFCC",
    "spectral-analysis",
    "voice-cloning"
  ],
  "version": "1.0.0",
  "author": "mukul975",
  "license": "Apache-2.0",
  "atlas_techniques": [
    "AML.T0088",
    "AML.T0043",
    "AML.T0018",
    "AML.T0052"
  ],
  "nist_ai_rmf": [
    "MEASURE-2.7",
    "GOVERN-6.2",
    "MAP-5.2",
    "MEASURE-2.5",
    "MAP-5.1"
  ],
  "d3fend_techniques": [
    "Sender Reputation Analysis",
    "Content Validation",
    "Message Analysis",
    "User Behavior Analysis",
    "Identifier Analysis"
  ],
  "nist_csf": [
    "PR.AT-01",
    "DE.CM-09",
    "RS.CO-02"
  ],
  "mitre_attack": [
    "T1078",
    "T1190",
    "T1059",
    "T1566",
    "T1598"
  ],
  "mitre_f3": {
    "version": "1.1",
    "tactics": [
      "reconnaissance",
      "initial-access",
      "stealth",
      "monetization"
    ],
    "techniques": [
      {
        "id": "F1032",
        "name": "Impersonate Official",
        "tactic": "initial-access",
        "source": "f3"
      },
      {
        "id": "F1031",
        "name": "Impersonate Account Holder",
        "tactic": "initial-access",
        "source": "f3"
      },
      {
        "id": "F1040",
        "name": "Phone Number Spoofing",
        "tactic": "stealth",
        "source": "f3"
      },
      {
        "id": "F1034",
        "name": "Interactive Voice Response Mapping",
        "tactic": "reconnaissance",
        "source": "f3"
      },
      {
        "id": "F1025.003",
        "name": "Electronic Funds Transfer: Wire Transfer",
        "tactic": "monetization",
        "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
    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: Audio Preprocessing

    Source-described action candidate under “Step 1: Audio Preprocessing”; not verified execution.

  4. 04
    Action

    Step 2: Extract Spectral Features

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

  5. 05
    Action

    Extract the feature set that distinguishes real from synthetic speech:

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

  6. 06
    Action

    Reduced spectral contrast in the 4-8 kHz range (vocoders compress high-frequency detail)

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

Inspect all extracted workflow candidates (23 candidate steps)
  1. 07
    Action

    Abnormally consistent spectral centroid over time (real speech has natural variation)

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

  2. 08
    Action

    Lower zero-crossing rate variance (synthetic speech lacks micro-perturbations)

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

  3. 09
    Action

    Missing or attenuated formant transitions during consonant-vowel boundaries

    Source-described action candidate under “Step 2: Extract Spectral Features”; not verified execution.

  4. 10
    Action

    Step 3: Build Feature Vector and Classify

    Source-described action candidate under “Step 3: Build Feature Vector and Classify”; not verified execution.

  5. 11
    Action

    Step 4: Temporal Artifact Analysis

    Source-described action candidate under “Step 4: Temporal Artifact Analysis”; not verified execution.

  6. 12
    Action

    Step 5: Spectrogram Visual Inspection

    Source-described action candidate under “Step 5: Spectrogram Visual Inspection”; not verified execution.

  7. 13
    Action

    Generate spectrograms for manual forensic review:

    Source-described action candidate under “Step 5: Spectrogram Visual Inspection”; not verified execution.

  8. 14
    Output

    Step 6: Generate Forensic Report

    Source-described output candidate under “Step 6: Generate Forensic Report”; not verified execution.

  9. 15
    Action

    Key Concepts

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

  10. 16
    Action

    Tools & Systems

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

  11. 17
    Action

    Common Scenarios

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

  12. 18
    Action

    Extract the audio from the phone system recording and convert to WAV at 16kHz

    Source-described action candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; not verified execution.

  13. 19
    Action

    Run MFCC and spectral feature extraction on the suspect audio

    Source-described action candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; not verified execution.

  14. 20
    Action

    Compare against known genuine CEO voice samples from recorded meetings

    Source-described action candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; not verified execution.

  15. 21
    Action

    Analyze pitch jitter and shimmer against human speech baselines

    Source-described action candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; not verified execution.

  16. 22
    Action

    Classify using the trained ensemble model and generate confidence score

    Source-described action candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; not verified execution.

  17. 23
    Output

    Produce forensic report with spectrogram evidence for legal/compliance

    Source-described output candidate under “Scenario: Executive Impersonation Wire Transfer Fraud”; 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

40 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

5 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 5 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

35 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 35 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-deepfake-audio-in-vishing-attacks/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/detecting-deepfake-audio-in-vishing-attacks/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-deepfake-audio-in-vishing-attacks
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.