hunting-credential-dumping-activity

hunting-credential-dumping-activity is a skill for Claude Code, Codex from meltedinhex/analyst-ai-pack. It costs 77 tokens per session (751 once invoked), scanned C, original, Apache-2.0.

A Windows security hunt for attempts to read LSASS, the Windows process that holds authentication secrets, or dump credentials from it. It uses Sysmon process-access and process-creation records.

In plain words
What is it for?
It helps find suspicious LSASS access, Mimikatz or ProcDump use, comsvcs MiniDump activity, dump files, and possible transfers of the stolen data.
Why use it?
Attackers may try to steal passwords and other authentication material from LSASS after gaining access to a computer. The hunt helps distinguish those attempts from legitimate security software activity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps find suspicious LSASS access, Mimikatz or ProcDump use, comsvcs MiniDump activity, dump files, and possible transfers of the stolen data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity
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 meltedinhex/analyst-ai-pack --skill hunting-credential-dumping-activity
Clone the repo
git clone --depth 1 https://github.com/meltedinhex/analyst-ai-pack

Made for: Claude Code, Codex.

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 hunting-credential-dumping-activity

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity/github.svg)](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity)
Your own site
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity/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 hunting-credential-dumping-activity

Your own site · 80×15
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-credential-dumping-activity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 751 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00077 $0.00751
Opus 5 $0.00039 $0.00376
Sonnet 5 $0.00015 $0.00150
Haiku 4.5 $0.00008 $0.00075

Measured 7d ago against content hash c239801bbebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

hunting-credential-dumping-activity scanned grade C with 1 finding 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyst.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

attempts to read LSASS memory or dump credentials.
skills/hunting-credential-dumping-activity/SKILL.md · 88 lines

What it actually says

Hunting Credential Dumping Activity

When to Use

  • You have Sysmon ProcessAccess (Event ID 10) and/or process-creation telemetry and want to detect attempts to read LSASS memory or dump credentials.
  • You are investigating post-exploitation credential theft.

Do not use this to dump credentials yourself — it analyzes telemetry of such activity. Legit security tools also touch LSASS; corroborate before alerting.

Prerequisites

  • Sysmon EID 10 events (with TargetImage, GrantedAccess, SourceImage) and/or EID 1 process events.

Workflow

Step 1: Hunt LSASS access and dumping patterns

python scripts/analyst.py hunt events.csv

Flags EID 10 events where TargetImage is lsass.exe with high-risk GrantedAccess masks (0x1010, 0x1410, 0x143a, 0x1438), and process events showing comsvcs.dll,MiniDump, procdump ... lsass, rundll32 ... MiniDump, or known tool names.

Step 2: Reduce false positives

De-prioritize known security agents (EDR, AV) as the SourceImage; weight unsigned or unusual source processes.

Step 3: Confirm

Correlate with file writes of .dmp files and subsequent off-host transfer.

Step 4: Operationalize

Write a Sigma rule for LSASS access masks and comsvcs MiniDump.

Validation

  • LSASS access flags are based on access mask, not mere access by trusted tools.
  • comsvcs/procdump/rundll32 MiniDump patterns are detected from command lines.
  • Findings map to ATT&CK T1003.001/.002.

Pitfalls

  • Many legitimate tools open LSASS — access mask + source-image context is essential.
  • Attackers renaming tools; rely on behavior (mask, MiniDump export) not just names.
  • Direct-syscall dumpers that avoid the usual API and reduce telemetry.

References

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 88 lines · 77 tokens per session scan C c239801bbebe

Subscribe to this mod's changes

hunting-credential-dumping-activity is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 751 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

analyzing-cobalt-strike-beacon-configuration

Extract and analyze Cobalt Strike beacon configuration from PE files and memory dumps to identify C2 infrastructure, malleable profiles, and operator tradecraft.

mukul975/Anthropic-Cybersecurity-Skills · 42 tokens

analyzing-golang-malware-with-ghidra

Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…

mukul975/Anthropic-Cybersecurity-Skills · 95 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

hunting-for-registry-run-key-persistence

Use when detect MITRE ATT&CK T1547.001 registry Run key persistence by analyzing Sysmon Event ID 13 logs and registry queries to identify malicious auto-start entries. Use when detecting mitre att&ck t1547.001 registry run key persistence by analyzing.

oyi77/1ai-skills · 66 tokens

analyzing-malicious-pdf-with-peepdf

A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.

killvxk/cybersecurity-skills-zh · 50 tokens

windows-event-logs-analysis

Conduct comprehensive forensic analysis of Windows Event Logs (.evtx) to trace attacker activity including lateral movement, privilege escalation, credential dumping, persistence mechanisms, and remote code execution. Use this skill during incident response, threat hunting, or post-breach forensic investigations on…

akashrpatil/awesome-offensive-security-skills · 64 tokens