Back to catalog
Static reviewDevelopment

Skill dossier

conducting-social-engineering-pretext-call

Source declaration

Plan and execute authorized vishing (voice phishing) pretext calls to assess employee susceptibility to social engineering and evaluate security awareness controls.

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

Plan and execute authorized vishing (voice phishing) pretext calls to assess employee susceptibility to social engineering and evaluate security awareness controls.

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.

Plan and execute authorized vishing (voice phishing) pretext calls to assess employee susceptibility to social engineering and evaluate security awareness controls. 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

  • Source-declared purpose: Plan and execute authorized vishing (voice phishing) pretext calls to assess employee susceptibility to social engineering and evaluate security awareness controls. [Evidence: skills/conducting-social-engineering-pretext-call/SKILL.md:L1-L72]
  • Provisional classification: category and tags are inferred from names, descriptions, and file paths, not verified outcomes. [Evidence: skills/conducting-social-engineering-pretext-call/SKILL.md:L1-L72]

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/conducting-social-engineering-pretext-call/SKILL.md:L1-L72]

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
44.1 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/conducting-social-engineering-pretext-call/assets/template.mdReference1.9 KB
skills/conducting-social-engineering-pretext-call/LICENSEOther11 KB
skills/conducting-social-engineering-pretext-call/references/api-reference.mdReference1.9 KB
skills/conducting-social-engineering-pretext-call/references/standards.mdReference1.4 KB
skills/conducting-social-engineering-pretext-call/references/workflows.mdReference4.6 KB
skills/conducting-social-engineering-pretext-call/scripts/agent.pyScript5.3 KB
skills/conducting-social-engineering-pretext-call/scripts/process.pyScript10 KB
skills/conducting-social-engineering-pretext-call/SKILL.mdInstruction8 KB

SKILL.md frontmatter

{
  "name": "conducting-social-engineering-pretext-call",
  "description": "Plan and execute authorized vishing (voice phishing) pretext calls to assess employee susceptibility to social engineering and evaluate security awareness controls.",
  "domain": "cybersecurity",
  "subdomain": "red-teaming",
  "tags": [
    "social-engineering",
    "vishing",
    "pretext-call",
    "security-awareness",
    "red-team",
    "phishing",
    "human-risk"
  ],
  "version": "1.0",
  "author": "mahipal",
  "license": "Apache-2.0",
  "atlas_techniques": [
    "AML.T0088",
    "AML.T0052"
  ],
  "nist_ai_rmf": [
    "GOVERN-6.2",
    "MAP-5.2"
  ],
  "d3fend_techniques": [
    "File Metadata Consistency Validation",
    "Application Protocol Command Analysis",
    "Identifier Analysis",
    "Content Format Conversion",
    "Message Analysis"
  ],
  "nist_csf": [
    "ID.RA-01",
    "GV.OV-02",
    "DE.AE-07"
  ],
  "mitre_attack": [
    "T1598.004",
    "T1566.004",
    "T1589",
    "T1591",
    "T1598"
  ],
  "mitre_f3": {
    "version": "1.1",
    "tactics": [
      "reconnaissance",
      "initial-access",
      "stealth"
    ],
    "techniques": [
      {
        "id": "T1598",
        "name": "Phishing for Information",
        "tactic": "reconnaissance",
        "source": "attack"
      },
      {
        "id": "F1034",
        "name": "Interactive Voice Response Mapping",
        "tactic": "reconnaissance",
        "source": "f3"
      },
      {
        "id": "F1029",
        "name": "Gather Customer Information",
        "tactic": "reconnaissance",
        "source": "f3"
      },
      {
        "id": "F1032",
        "name": "Impersonate Official",
        "tactic": "initial-access",
        "source": "f3"
      },
      {
        "id": "F1040",
        "name": "Phone Number Spoofing",
        "tactic": "stealth",
        "source": "f3"
      },
      {
        "id": "F1040.002",
        "name": "Phone Number Spoofing: Official Phone Number Spoofing",
        "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

    MITRE ATT&CK Mapping

    Source-described action candidate under “MITRE ATT&CK Mapping”; not verified execution.

  4. 04
    Action

    Phase 1: OSINT and Target Research

    Source-described action candidate under “Phase 1: OSINT and Target Research”; not verified execution.

  5. 05
    Action

    Phase 2: Pretext Development

    Source-described action candidate under “Phase 2: Pretext Development”; not verified execution.

  6. 06
    Action

    Phase 3: Call Execution

    Source-described action candidate under “Phase 3: Call Execution”; not verified execution.

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

    Introduction (10 seconds): State name, department, reason for calling

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

  2. 08
    Action

    Building rapport (30 seconds): Reference something real (recent event, shared context)

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

  3. 09
    Action

    Authority establishment (20 seconds): Reference manager name, ticket number, urgency

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

  4. 10
    Action

    Information request (30 seconds): Ask for the target information naturally

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

  5. 11
    Decision

    Handling objections: If challenged, respond calmly with prepared answers

    Source-described decision candidate under “Call Structure”; not verified execution.

  6. 12
    Action

    Closing (10 seconds): Thank them, leave no suspicion

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

  7. 13
    Action

    Phase 4: Data Collection and Metrics

    Source-described action candidate under “Phase 4: Data Collection and Metrics”; not verified execution.

  8. 14
    Action

    Phase 5: Reporting

    Source-described action candidate under “Phase 5: Reporting”; not verified execution.

  9. 15
    Action

    Ethical and Legal Considerations

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  10. 16
    Action

    Always obtain written authorization before conducting vishing tests

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  11. 17
    Action

    Never use threatening language or create genuine fear

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  12. 18
    Action

    Document consent and legal requirements for call recording

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  13. 19
    Output

    Protect disclosed credentials - immediately report to client

    Source-described output candidate under “Ethical and Legal Considerations”; not verified execution.

  14. 20
    Decision

    Debrief targets after the engagement if client approves

    Source-described decision candidate under “Ethical and Legal Considerations”; not verified execution.

  15. 21
    Action

    Never publicly identify specific employees who failed

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  16. 22
    Action

    Comply with telecommunications laws in your jurisdiction

    Source-described action candidate under “Ethical and Legal Considerations”; not verified execution.

  17. 23
    Action

    References

    Source-described action candidate under “References”; 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

28 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

22 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 22 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

6 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 6 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/conducting-social-engineering-pretext-call/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/conducting-social-engineering-pretext-call/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/conducting-social-engineering-pretext-call
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.