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.
npx skills add Liberty91LTD/cti-skills --skill phishing-social-engineeringgit clone --depth 1 https://github.com/Liberty91LTD/cti-skillsWrote 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.
[](https://agentmods.dev/skills/liberty91ltd/cti-skills/phishing-social-engineering)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.07382 |
| Opus 5.5 | $0.00022 | $0.02953 |
| Sonnet 5.5 | $0.00011 | $0.01476 |
| Haiku 4.5 | $0.00006 | $0.00738 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 199 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 among the most common initial access vectors across both cybercriminal and state-sponsored operations. Microsoft's 2025 Digital Defense Report attributes 28% of the breaches its incident responders investigated to phishing or social engineering [39]. The defining change since 2024 is that attackers increasingly avoid stealing a password at all. Three techniques now sit alongside Adversary-in-the-Middle (AitM) session theft: device code phishing, where the victim authorizes an attacker's device on the genuine Microsoft sign-in page; ClickFix, where a fake CAPTCHA or error page talks the victim into pasting and running a command; and voice phishing, where a caller posing as the IT help desk walks an employee through handing over access. All three defeat non-phishing-resistant MFA, and the consistent vendor recommendation is FIDO2/passkey authentication, restriction of the device code flow, and managed-device requirements.
The Phishing-as-a-Service (PhaaS) market was the target of four major disruptions in twelve months: RaccoonO365 (September 2025), Tycoon 2FA (March 2026), the China-based Outsider kit (June 2026) and EvilTokens (September 2026) [10][17][19][34]. Results were mixed. Tycoon 2FA, which Microsoft says accounted for about 62% of the phishing attempts it blocked by mid-2025, lost 330 domains but was back at pre-disruption volume within days according to CrowdStrike, and by late April 2026 had added device code phishing [10][11][13]. Outsider affiliates stood up more than 700 new phishing pages in the month after the takedown [33]. EvilTokens, launched in February 2026, turned device code phishing into a commodity and bundled an AI assistant that triaged stolen mailboxes for payment fraud; its disruption was accompanied by two arrests in the UK, and it is too early to judge whether it holds [18][19]. Subscription prices observed in 2025-2026 range from $289 per month (Greatness) to a $1,500 entry fee plus $500 per month (EvilTokens) [19][23].
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.
- 1mo ago Changed · +74 lines 9d470608125d
- 2mo ago First seen · 125 lines · 55 tokens per session scan A b8807dc30fb6
phishing-social-engineering is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 7,382 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
analyzing-campaign-attribution-evidence
Systematically evaluate cyber-campaign evidence to attribute an operation to a threat actor, using the Diamond Model and Analysis of Competing Hypotheses (ACH) to weigh infrastructure overlaps, TTP consistency, malware code similarity, and timing/language artifacts into confidence-weighted attribution assessments. Use…
analyzing-threat-actor-ttps-with-mitre-attack
MITRE ATT&CK is a globally-accessible knowledge base of adversary tactics, techniques, and procedures (TTPs) based on real-world observations. This skill covers systematically mapping threat actor beh.
analyzing-threat-landscape-with-misp
Analyze the threat landscape using MISP (Malware Information Sharing Platform) by querying event statistics, attribute distributions, threat actor galaxy clusters, and tag trends over time. Uses PyMISP to pull event data, compute IOC type breakdowns, identify top threat actors and malware families, and generate threat…
analyzing-campaign-attribution-evidence
Use when campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.
prompt-injection-auditor
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
analyzing-campaign-attribution-evidence
Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.