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 infostealersgit 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/infostealers)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/infostealers"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/infostealers/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/infostealers"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/infostealers.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 | $0.00072 | $0.06666 |
| Opus 5.5 | $0.00029 | $0.02666 |
| Sonnet 5.5 | $0.00014 | $0.01333 |
| Haiku 4.5 | $0.00007 | $0.00667 |
Grade A, and why
infostealers 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infostealers
Executive Summary
Infostealer malware remains a foundational enabler for ransomware, account takeover, corporate network intrusion, and financial fraud. The families operate under a Malware-as-a-Service (MaaS) model: developers sell subscriptions that include a builder, a management panel, and regular updates to evade detection. Upon execution, infostealers harvest browser-stored credentials, session cookies, cryptocurrency wallet data, autofill data, and system information, packaging the results into "logs" that are sold on marketplaces, traded on Telegram, or used directly by the operator.
Between May 2025 and June 2026 the three families that led the market after RedLine's 2024 disruption were each hit by coordinated action: Lumma (May 2025, Microsoft, US DOJ, Europol and JC3), Rhadamanthys (November 2025, Operation Endgame), and StealC together with the Amadey loader (June 2026, Operation Endgame) [9][10][17][21][22]. None of these actions announced an arrest of a stealer developer. The results differ by family. Lumma rebuilt after the May 2025 seizures, then lost customers after rivals doxxed its alleged core members between late August and October 2025; it remains in circulation at reduced standing [13][14][28]. Rhadamanthys' developer attempted a revival about three weeks after the takedown, without new releases [19]. The post-takedown state of StealC is not yet established in the sources reviewed.
The market is now fragmented. Vidar, relaunched as version 2.0 in October 2025, absorbed much of the displaced demand [13][15][19]. Acreed rose on Russian Market during 2025 [11][12]. Newer names, including Remus, RevStealer and a set of macOS stealers (MacSync, Shub Stealer, DigitStealer), appear in 2026 vendor reporting [25][26][27][29]. Russian Market continues to operate, but Flare reports that more than 90% of the stealer logs it sees are now found on Telegram [28]. BidenCash was seized by US authorities in June 2025 [31].
Delivery has shifted towards ClickFix: fake verification or troubleshooting pages that persuade the user to paste and run a command. Microsoft describes campaigns hitting thousands of devices daily and, in 2026, macOS variants that fingerprint visitors before showing the lure [23][24][25]. The infostealer-to-ransomware link through Initial Access Brokers (IABs) is unchanged, while the value of a log has widened: Flare found enterprise SSO or identity-provider credentials in 2.05 million of 18.7 million logs analysed for 2025, and in 2026 stolen sessions for AI services became a reported monetisation path [28][32][33].
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 · +59 lines 6493b9da93c9
- 2mo ago First seen · 124 lines · 72 tokens per session scan A d5bb71f9d45a
infostealers is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 6,666 once invoked, about $0.0003 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 2026-08-30.
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.