CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conducting-social-engineering-penetration-test

Design and execute a social engineering penetration test combining OSINT-driven target profiling with phishing, vishing, smishing, and physical pretexting campaigns using tools like GoPhish, the Social Engineer Toolkit (SET), and Evilginx to measure human security resilience. Use when scoping or running an authorized human-attack-surface test and reporting results to identify security awareness training gaps.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and reasonably token-efficient, with concrete commands, templates, and metrics throughout a clearly phased workflow. Its main weaknesses are absent validation checkpoints for a risky batch operation and failure to use the existing reference bundle, leaving large detail blocks inlined in SKILL.md.

Suggestions

Add explicit validation checkpoints between phases: verify infrastructure with a test send to controlled accounts, confirm SPF/DKIM/DMARC on the attack domain, and validate landing-page capture before launching the batch campaign.

Link the existing bundle files from the body (e.g. 'GoPhish API details: see references/api-reference.md', 'Campaign lifecycle: see references/workflows.md') and move the email templates and tools table into references/ to slim SKILL.md.

Trim the Verizon DBIR sentence, the 'When to Use' section that duplicates the frontmatter description, and the hardcoded 2025 dates in example templates, which are time-sensitive and will age poorly.

DimensionReasoningScore

Conciseness

The body is dense with commands, templates, and tables and assumes domain competence, but contains trimmable material: the Verizon DBIR statistic sentence, a 'When to Use' section that duplicates the frontmatter, and time-dated example content ('Q1 2025', 'March 15, 2025') that is not isolated in a deprecated section.

4 / 5

Actionability

Mostly executable guidance: real theHarvester/dig/Evilginx commands, GoPhish campaign JSON, and complete email and vishing scripts. Minor gaps remain, e.g. 'sudo apt install gophish' is not an actual apt package, the campaign JSON is illustrative rather than an API payload, and the email HTML is elided.

4 / 5

Workflow Clarity

Phases 1-6 provide a clear sequence from OSINT through reporting, but a batch campaign against 200 employees has no validation checkpoints (no test send, no infrastructure verification, no pre-launch DMARC/SPF checks), which caps workflow clarity at 3 per the batch-operation rule.

3 / 5

Progressive Disclosure

The phase structure is well organized, but the body never links to the existing bundle files (references/api-reference.md, workflows.md, standards.md, scripts/, assets/template.md), and large email templates and tool/API reference blocks that belong in those files are inlined in SKILL.md.

3 / 5

Total

14

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities with named tools and vectors, includes an explicit and specific 'Use when' clause, and occupies a distinct niche. The only weakness is a few missing natural trigger synonyms such as 'phishing simulation'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ('OSINT-driven target profiling with phishing, vishing, smishing, and physical pretexting campaigns') and names specific tools (GoPhish, SET, Evilginx), giving comprehensive capability coverage in third-person voice.

5 / 5

Completeness

It explicitly answers both 'what' (design and execute a social engineering penetration test with named vectors and tools) and 'when' ('Use when scoping or running an authorized human-attack-surface test and reporting results to identify security awareness training gaps').

5 / 5

Trigger Term Quality

Natural keywords like 'phishing', 'vishing', 'smishing', 'pretexting', 'OSINT', and 'security awareness training' are present, but common user phrasings such as 'phishing simulation' or 'phishing test' are missing.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (authorized human-attack-surface testing) with distinct trigger phrases, so it is unlikely to fire for unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

mukul975/Anthropic-Cybersecurity-Skills

Path

skills/conducting-social-engineering-penetration-test/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.