phishing-social-engineering

phishing-social-engineering is a skill for Claude Code from Liberty91LTD/cti-skills. It costs 55 tokens per session (2,822 once invoked), scanned A, original, MIT.

A security knowledge guide about phishing and social engineering, including attacks that trick people into revealing credentials or approving access. It covers business email compromise, fake login systems, and methods that can intercept login sessions.

In plain words
What is it for?
It helps with defensive analysis of phishing campaigns, social-engineering techniques, phishing-kit families, and protections such as phishing-resistant login methods.
Why use it?
It explains how these attacks work and why ordinary multi-factor authentication may not stop every phishing method.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument.

Good fit It helps with defensive analysis of phishing campaigns, social-engineering techniques, phishing-kit families, and protections such as phishing-resistant login methods.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liberty91ltd/cti-skills/phishing-social-engineering
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Liberty91LTD/cti-skills --skill phishing-social-engineering
Clone the repo
git clone --depth 1 https://github.com/Liberty91LTD/cti-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for phishing-social-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/phishing-social-engineering/github.svg)](https://agentmods.dev/skills/liberty91ltd/cti-skills/phishing-social-engineering)
Your own site
<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/phishing-social-engineering"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/phishing-social-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for phishing-social-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/phishing-social-engineering"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/phishing-social-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02822
Opus 5 $0.00028 $0.01411
Sonnet 5 $0.00011 $0.00564
Haiku 4.5 $0.00006 $0.00282

Measured 9d ago against content hash b8807dc30fb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

phishing-social-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/phishing-social-engineering/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phishing & Social Engineering

Executive Summary

Phishing and social engineering remain the most common initial access vectors across both cybercriminal and state-sponsored operations. The landscape has undergone significant evolution beyond traditional email-based credential harvesting. Adversary-in-the-Middle (AitM) phishing platforms — notably EvilProxy and Evilginx — now enable real-time interception of credentials AND session tokens, effectively bypassing most forms of multi-factor authentication (MFA). This development has fundamentally altered the threat model for organizations relying on MFA as a primary defense, shifting the security boundary toward phishing-resistant MFA methods such as FIDO2/WebAuthn hardware keys.

The Phishing-as-a-Service (PhaaS) market has matured substantially, with platforms like EvilProxy, Greatness, Tycoon 2FA, and others offering turnkey AitM phishing kits with subscription models, customer support, and real-time dashboards. These services target Microsoft 365 accounts disproportionately, reflecting the platform's dominance in enterprise environments. Pricing ranges from $200-$1,000+ per month depending on features and target capabilities. Meanwhile, Business Email Compromise (BEC) continues to generate the highest financial losses of any cybercrime category according to FBI IC3 data — over $2.9 billion in reported losses in 2023 alone — despite being less technically sophisticated than other threats.

Emerging vectors include QR code phishing ("quishing"), which evades email security gateways by embedding malicious URLs in images; vishing and callback phishing campaigns that move victims to phone conversations to bypass email controls; AI-generated deepfake voice and video for executive impersonation; and consent phishing that abuses OAuth application permissions to gain persistent access to cloud mailboxes. The combination of AI-enhanced content generation (eliminating grammatical tells), sophisticated infrastructure (legitimate cloud hosting, CAPTCHA protection, geofencing), and AitM session hijacking has made modern phishing significantly harder to detect and defend against.

Read the full file on GitHub · 125 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 125 lines · 55 tokens per session scan A b8807dc30fb6

Subscribe to this mod's changes

phishing-social-engineering is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,822 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.