Authorization Bypass Detection
Tencent/AI-Infra-Guard
Probes an AI agent through dialogue for cross-user data access, privilege escalation and login bypass, and reports confirmed findings as structured vulnerability entries.
Agent skill
Extract, parse, and analyze Windows Event Logs (EVTX) using Chainsaw, Hayabusa, and EvtxECmd to detect lateral movement, persistence, and privilege escalation.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifacts --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .claude/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .claude/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifactsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifacts --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .agents/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .agents/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifacts --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .cursor/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .cursor/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/extracting-windows-event-logs-artifacts--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifacts --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .gemini/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .gemini/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifactsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .github/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .github/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills extracting-windows-event-logs-artifacts --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/extracting-windows-event-logs-artifacts .opencode/skills/extracting-windows-event-logs-artifacts && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "extracting-windows-event-logs-artifacts" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/extracting-windows-event-logs-artifacts into .opencode/skills/extracting-windows-event-logs-artifacts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-windows-event-logs-artifacts", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
extracting-windows-event-logs-artifactsExtract, parse, and analyze Windows Event Logs (EVTX) using Chainsaw, Hayabusa, and EvtxECmd to detect lateral movement, persistence, and privilege escalation.
Extracting Windows Event Logs Artifacts is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Extract, parse, and analyze Windows Event Logs (EVTX) using Chainsaw, Hayabusa, and EvtxECmd to detect lateral movement, persistence, and privilege escalation.
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).
It sits in Security, covering Red teaming and adversary simulation. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3wgetpipFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Extracting Windows Event Logs Artifacts loads about 3.3k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 467 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 467 words, ~3,265 tokens.
.claude/skills/extracting-windows-event-logs-artifacts/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.# Extract EVTX files from forensic image
mount -o ro,loop,offset=$((2048*512)) /cases/case-2024-001/images/evidence.dd /mnt/evidence
mkdir -p /cases/case-2024-001/evtx/
cp /mnt/evidence/Windows/System32/winevt/Logs/*.evtx /cases/case-2024-001/evtx/
# Key event logs to prioritize
# Security.evtx - Authentication, authorization, audit events
# System.evtx - System services, drivers, hardware events
# Application.evtx - Application errors and events
# Microsoft-Windows-Sysmon%4Operational.evtx - Detailed process/network monitoring
# Microsoft-Windows-PowerShell%4Operational.evtx - PowerShell activity
# Microsoft-Windows-TerminalServices-LocalSessionManager%4Operational.evtx - RDP sessions
# Microsoft-Windows-TaskScheduler%4Operational.evtx - Scheduled tasks
# Microsoft-Windows-WinRM%4Operational.evtx - Windows Remote Management
# Microsoft-Windows-Bits-Client%4Operational.evtx - BITS transfers
# Microsoft-Windows-Windows Defender%4Operational.evtx - AV detections
# List available log files and sizes
ls -lhS /cases/case-2024-001/evtx/ | head -20
# Hash for integrity
sha256sum /cases/case-2024-001/evtx/*.evtx > /cases/case-2024-001/evtx/evtx_hashes.txt# Install Chainsaw
wget https://github.com/WithSecureLabs/chainsaw/releases/latest/download/chainsaw_all_platforms+rules.zip
unzip chainsaw_all_platforms+rules.zip -d /opt/chainsaw
# Run Chainsaw with bundled Sigma rules
/opt/chainsaw/chainsaw hunt /cases/case-2024-001/evtx/ \
-s /opt/chainsaw/sigma/rules/ \
--mapping /opt/chainsaw/mappings/sigma-event-logs-all.yml \
--output /cases/case-2024-001/analysis/chainsaw_results.txt
# Run with CSV output for easier analysis
/opt/chainsaw/chainsaw hunt /cases/case-2024-001/evtx/ \
-s /opt/chainsaw/sigma/rules/ \
--mapping /opt/chainsaw/mappings/sigma-event-logs-all.yml \
--csv \
--output /cases/case-2024-001/analysis/chainsaw_results/
# Run with JSON output
/opt/chainsaw/chainsaw hunt /cases/case-2024-001/evtx/ \
-s /opt/chainsaw/sigma/rules/ \
--mapping /opt/chainsaw/mappings/sigma-event-logs-all.yml \
--json \
--output /cases/case-2024-001/analysis/chainsaw_results.json
# Search for specific keywords
/opt/chainsaw/chainsaw search /cases/case-2024-001/evtx/ \
-s "mimikatz" --json
# Search for specific event IDs
/opt/chainsaw/chainsaw search /cases/case-2024-001/evtx/ \
-e 4688 --json | head -100# Install Hayabusa
wget https://github.com/Yamato-Security/hayabusa/releases/latest/download/hayabusa-linux-x64-musl.zip
unzip hayabusa-linux-x64-musl.zip -d /opt/hayabusa
# Generate CSV timeline with all detection rules
/opt/hayabusa/hayabusa csv-timeline \
-d /cases/case-2024-001/evtx/ \
-o /cases/case-2024-001/analysis/hayabusa_timeline.csv \
-p verbose
# Generate JSON timeline
/opt/hayabusa/hayabusa json-timeline \
-d /cases/case-2024-001/evtx/ \
-o /cases/case-2024-001/analysis/hayabusa_timeline.json
# Run with only critical and high severity detections
/opt/hayabusa/hayabusa csv-timeline \
-d /cases/case-2024-001/evtx/ \
-o /cases/case-2024-001/analysis/hayabusa_critical.csv \
-p verbose \
--min-level critical
# Generate detection summary (metrics)
/opt/hayabusa/hayabusa metrics \
-d /cases/case-2024-001/evtx/ \
-o /cases/case-2024-001/analysis/hayabusa_metrics.csv
# Logon summary
/opt/hayabusa/hayabusa logon-summary \
-d /cases/case-2024-001/evtx/ \
-o /cases/case-2024-001/analysis/logon_summary.csv# Extract authentication events with python-evtx
pip install evtx
python3 << 'PYEOF'
import json
from evtx import PyEvtxParser
parser = PyEvtxParser("/cases/case-2024-001/evtx/Security.evtx")
# Critical Event IDs mapping
critical_events = {
'4624': 'Successful Logon',
'4625': 'Failed Logon',
'4634': 'Logoff',
'4648': 'Explicit Credential Logon',
'4672': 'Special Privileges Assigned',
'4688': 'Process Created',
'4689': 'Process Exited',
'4697': 'Service Installed',
'4698': 'Scheduled Task Created',
'4720': 'User Account Created',
'4724': 'Password Reset Attempted',
'4728': 'Member Added to Global Group',
'4732': 'Member Added to Local Group',
'4756': 'Member Added to Universal Group',
'1102': 'Audit Log Cleared',
'4688': 'New Process Created'
}
results = {eid: [] for eid in critical_events}
for record in parser.records_json():
data = json.loads(record['data'])
event_id = str(data['Event']['System']['EventID'])
if event_id in critical_events:
event_data = data['Event'].get('EventData', {})
results[event_id].append({
'timestamp': data['Event']['System']['TimeCreated']['#attributes']['SystemTime'],
'event_id': event_id,
'description': critical_events[event_id],
'data': event_data
})
# Print summary
for eid, events in results.items():
if events:
print(f"\n[{eid}] {critical_events[eid]}: {len(events)} events")
for e in events[:3]:
print(f" {e['timestamp']}: {json.dumps(e['data'], default=str)[:200]}")
if len(events) > 3:
print(f" ... and {len(events)-3} more")
# Save full results
with open('/cases/case-2024-001/analysis/critical_events.json', 'w') as f:
json.dump(results, f, indent=2, default=str)
PYEOF# Detect Pass-the-Hash (Logon Type 9 with NTLM)
python3 << 'PYEOF'
import json
from evtx import PyEvtxParser
parser = PyEvtxParser("/cases/case-2024-001/evtx/Security.evtx")
print("=== PASS-THE-HASH INDICATORS ===")
print("Looking for: Event 4624, Logon Type 9, NTLM authentication\n")
for record in parser.records_json():
data = json.loads(record['data'])
event_id = str(data['Event']['System']['EventID'])
if event_id == '4624':
event_data = data['Event'].get('EventData', {})
logon_type = str(event_data.get('LogonType', ''))
auth_package = str(event_data.get('AuthenticationPackageName', ''))
logon_process = str(event_data.get('LogonProcessName', ''))
# Pass-the-Hash indicators
if logon_type == '9' and 'NTLM' in auth_package:
timestamp = data['Event']['System']['TimeCreated']['#attributes']['SystemTime']
target = event_data.get('TargetUserName', 'Unknown')
source_ip = event_data.get('IpAddress', 'N/A')
print(f" [{timestamp}] PtH: User={target}, IP={source_ip}, Auth={auth_package}")
# Network logon with NTLM (lateral movement)
if logon_type == '3' and 'NTLM' in auth_package:
timestamp = data['Event']['System']['TimeCreated']['#attributes']['SystemTime']
target = event_data.get('TargetUserName', 'Unknown')
source_ip = event_data.get('IpAddress', 'N/A')
workstation = event_data.get('WorkstationName', 'N/A')
print(f" [{timestamp}] Network NTLM: User={target}, IP={source_ip}, WS={workstation}")
PYEOF
# Detect log clearing / anti-forensics
python3 << 'PYEOF'
import json
from evtx import PyEvtxParser
for log_file in ['Security.evtx', 'System.evtx']:
path = f"/cases/case-2024-001/evtx/{log_file}"
try:
parser = PyEvtxParser(path)
for record in parser.records_json():
data = json.loads(record['data'])
event_id = str(data['Event']['System']['EventID'])
if event_id in ('1102', '104'): # Security log cleared, System log cleared
timestamp = data['Event']['System']['TimeCreated']['#attributes']['SystemTime']
print(f"LOG CLEARED: [{timestamp}] EventID {event_id} in {log_file}")
except Exception as e:
print(f"Error parsing {log_file}: {e}")
PYEOF| Concept | Description |
|---|---|
| EVTX format | Binary XML-based Windows Event Log format introduced in Vista/Server 2008 |
| Event ID | Numeric identifier for specific event types (e.g., 4624 = successful logon) |
| Logon types | Classification of authentication methods (2=interactive, 3=network, 10=RDP) |
| Sigma rules | Generic detection signatures that map to specific SIEM/log queries |
| Sysmon | Microsoft system monitoring driver providing detailed process and network events |
| Audit policy | GPO settings controlling which events Windows records |
| Event forwarding (WEF) | Windows mechanism for centralized event log collection |
| EVTX channels | Separate log files for different event categories and applications |
| Tool | Purpose |
|---|---|
| Chainsaw | Sigma-based EVTX analysis and threat hunting tool |
| Hayabusa | Fast Windows Event Log forensic timeline generator |
| EvtxECmd | Eric Zimmerman command-line EVTX parser with CSV/JSON output |
| python-evtx | Python library for EVTX file parsing |
| LogParser | Microsoft SQL-like query engine for Windows logs |
| Event Log Explorer | GUI tool for browsing and analyzing EVTX files |
| KAPE | Automated triage collection including event logs |
| Velociraptor | Endpoint agent with EVTX collection and hunting artifacts |
Scenario 1: Detecting Lateral Movement Filter for Event 4624 with Logon Type 3 (network) and Type 10 (RDP), identify unusual source-destination pairs, check for Event 4648 (explicit credentials) indicating pass-the-hash, correlate with process creation events (4688) on target systems.
Scenario 2: Privilege Escalation Detection Search for Event 4672 (special privileges assigned) for unexpected users, check for Event 4728/4732 (group membership changes) adding users to admin groups, look for Event 4697 (service installed) indicating new system-level access, correlate with 4720 (account creation).
Scenario 3: PowerShell Attack Detection Analyze PowerShell Operational log for Script Block Logging (Event 4104), search for encoded commands in Event 4688 (process creation with command line), detect AMSI bypass attempts, identify download cradles and invocation of known attack tools.
Scenario 4: Ransomware Incident Reconstruction Build timeline starting from initial access (4624 from external IP), trace privilege escalation through group membership changes, identify service installations for persistence, find process creation events for encryption executable, detect volume shadow copy deletion in System log.
Windows Event Log Analysis Summary:
System: DC01.corp.local (Windows Server 2019)
Log Files Analyzed: 15 EVTX files
Total Events: 2,456,789
Analysis Period: 2024-01-10 to 2024-01-20
Chainsaw Detections:
Critical: 12 (Mimikatz usage, PsExec, log clearing)
High: 34 (Network NTLM logons, encoded PowerShell)
Medium: 89 (Unusual service installations, scheduled tasks)
Low: 234 (Informational)
Hayabusa Timeline:
Total Alerts: 369
Unique Rules Triggered: 45
Top Rules:
- Suspicious NTLM Authentication (34 hits)
- PowerShell Download Cradle (12 hits)
- Service Installation Suspicious Path (8 hits)
Critical Findings:
2024-01-15 14:32 - RDP brute force (234 failed, 1 success from 203.0.113.45)
2024-01-15 14:45 - Admin account created (svcbackup) - Event 4720
2024-01-16 02:30 - PsExec service installed on DC01 - Event 4697
2024-01-18 03:00 - Security log cleared - Event 1102
Reports:
Chainsaw: /analysis/chainsaw_results/
Hayabusa: /analysis/hayabusa_timeline.csv
Critical Events: /analysis/critical_events.json© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts, references) in skills/extracting-windows-event-logs-artifacts of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Extracting Windows Event Logs Artifacts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Extracting Windows Event Logs Artifacts this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Authorization Bypass DetectionTencent/AI-Infra-Guard | 6.8k | — | ~753 | Automated safety check: Pass | Apache-2.0 | |
| Run Assert Evalresponsibleai/ASSERT | 330 | — | ~11k | Automated safety check: Notes | MIT | |
| Osint Methodologyelementalsouls/Claude-OSINT | 2.8k | — | ~8.7k | Automated safety check: Notes | MIT | |
| Lfd Designelvisun/loss-function-development | 176 | — | ~2.9k | Automated safety check: Notes | MIT | |
| Acl AbuseADScanPro/Claude-AD | 211 | — | ~2.6k | Automated safety check: Pass | MIT |
Tencent/AI-Infra-Guard
Probes an AI agent through dialogue for cross-user data access, privilege escalation and login bypass, and reports confirmed findings as structured vulnerability entries.
responsibleai/ASSERT
Run an ASSERT evaluation against a described risk. An agent skill from responsibleai/ASSERT.
elementalsouls/Claude-OSINT
Comprehensive OSINT methodology for external red-team operations and authorized attack-surface assessments.
elvisun/loss-function-development
Design a loss function and harness for a long-running /goal optimization run (loss-function development, LFD).
ADScanPro/Claude-AD
Abusing Active Directory object ACLs (DACL/ownership) for privilege escalation and lateral movement (GenericAll, GenericWrite, WriteDACL, WriteOwner, AddMember, ForceChangePassword, and replication…
Tencent/AI-Infra-Guard
Probes whether an agent with web fetch and stored user memory can be tricked by a malicious page into leaking data through chained URL paths.
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Categories
Extract, parse, and analyze Windows Event Logs (EVTX) using Chainsaw, Hayabusa, and EvtxECmd to detect lateral movement, persistence, and privilege escalation. Extracting Windows Event Logs Artifacts is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Extract, parse, and analyze Windows Event Logs (EVTX) using Chainsaw, Hayabusa, and EvtxECmd to detect lateral movement, persistence, and privilege escalation.
Extracting Windows Event Logs Artifacts fits situations like: tasks that involve Red teaming and adversary simulation.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a claude-code`. Or copy the skill folder (skills/extracting-windows-event-logs-artifacts in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/extracting-windows-event-logs-artifacts in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a codex`. Or copy the skill folder (skills/extracting-windows-event-logs-artifacts in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/extracting-windows-event-logs-artifacts in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill extracting-windows-event-logs-artifacts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extracting-windows-event-logs-artifacts, .gemini/skills/extracting-windows-event-logs-artifacts, .github/skills/extracting-windows-event-logs-artifacts and .opencode/skills/extracting-windows-event-logs-artifacts in your project.
Going by SKILL.md and its folder, Extracting Windows Event Logs Artifacts needs Python for the scripts in its folder and the command-line tools its instructions call (python3, wget and pip). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Extracting Windows Event Logs Artifacts is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 705 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Extracting Windows Event Logs Artifacts: Authorization Bypass Detection (Tencent/AI-Infra-Guard, 6.8k stars), Run Assert Eval (responsibleai/ASSERT, 330 stars), Osint Methodology (elementalsouls/Claude-OSINT, 2.8k stars) and Lfd Design (elvisun/loss-function-development, 176 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 34,116 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.