Borrowing it
Nothing to install: this file belongs to kismatkunwar89/SAVVYDFIR-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kismatkunwar89/SAVVYDFIR-MCP/master/.claude/skills/sigma-detection/SKILL.mdgit clone --depth 1 https://github.com/kismatkunwar89/SAVVYDFIR-MCPWrote 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/kismatkunwar89/savvydfir-mcp/sigma-detection)<a href="https://agentmods.dev/skills/kismatkunwar89/savvydfir-mcp/sigma-detection"><img src="https://agentmods.dev/badge/skills/kismatkunwar89/savvydfir-mcp/sigma-detection/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/kismatkunwar89/savvydfir-mcp/sigma-detection"><img src="https://agentmods.dev/badge/skills/kismatkunwar89/savvydfir-mcp/sigma-detection.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 | $0.00043 | $0.00941 |
| Opus 5 | $0.00022 | $0.00470 |
| Sonnet 5 | $0.00009 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
sigma-detection 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sigma Detection - Universal Anomaly Detection Guide
How sigma_scan() Works
sigma_scan(case_id) reads ALL findings from the case state and runs 5 independent detectors. Each detector implements case-agnostic logic - no hardcoded IPs, usernames, or filenames.
Detector 1: Process Anomalies
What it checks:
- svchost.exe not spawned by services.exe → masquerading (T1036.005)
- System processes (smss, csrss, lsass, etc.) from non-System32 paths → masquerading
- Orphan processes (PPID points to non-existent process) → possible DKOM or parent terminated
When it fires CRITICAL:
- svchost wrong parent
- System process wrong path
Pivot from hit:
detect_injection(pid=FLAGGED_PID)- check for code injectionlist_dlls(pid=FLAGGED_PID)- check for suspicious DLLs- Hash the binary:
sha256sum <path>
Detector 2: Network Anomalies
What it checks:
- System processes (svchost, lsass, etc.) with external (non-RFC1918) connections → C2
- Outbound connections on non-standard ports (not 80/443/53/445/etc.) → covert channel
- Listening sockets owned by unexpected processes
RFC1918 exclusion logic:
- 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16 are IGNORED (normal internal traffic)
- Only external IPs trigger alerts
Pivot from hit:
- YARA scan memory for C2 signatures
- Check if the remote IP appears in other findings
- Timeline query around the connection timestamp
Detector 3: MFT Timestomping
What it checks:
- $STANDARD_INFORMATION Created vs $FILE_NAME Created
- If delta > 1 hour → timestomping detected (T1070.006)
- SI timestamps are user-modifiable; FN timestamps require kernel access
Pivot from hit:
- Check prefetch for true first execution time
- Check amcache for SHA-1 hash of the binary
run_analysis()on MFT CSV to find nearby file operations
Detector 4: EVTX High-Value Events
Auto-tagged events with ATT&CK mapping:
| EventID | Meaning | Tactic | Technique |
|---|---|---|---|
| 4624 | Logon success | TA0001 | T1078 |
| 4625 | Logon failure | TA0006 | T1110 |
| 4648 | Explicit logon | TA0008 | T1021 |
| 4672 | Special privileges | TA0004 | T1134 |
| 4688 | Process creation | TA0002 | T1059 |
| 4697 | Service installed | TA0003 | T1543 |
| 4698 | Scheduled task | TA0003 | T1053 |
| 4720 | User created | TA0003 | T1136 |
| 7045 | New service | TA0003 | T1543.003 |
| 1116 | Defender detection | TA0005 | T1562 |
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.
- 11d ago First seen · 84 lines · 43 tokens per session scan A 5e388adbf6a9
sigma-detection is a skill published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 941 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
forensics-osquery
SQL-powered forensic investigation and system interrogation using osquery to query operating systems as relational databases. Enables rapid evidence collection, threat hunting, and incident response across Linux, macOS, and Windows endpoints. Use when: (1) Investigating security incidents and collecting forensic…
ir-velociraptor
Endpoint visibility, digital forensics, and incident response using Velociraptor Query Language (VQL) for evidence collection and threat hunting at scale. Use when: (1) Conducting forensic investigations across multiple endpoints, (2) Hunting for indicators of compromise or suspicious activities, (3) Collecting…
performing-cloud-forensics-with-aws-cloudtrail
Perform forensic investigation of AWS environments using CloudTrail logs to reconstruct attacker activity, identify compromised credentials, and analyze API call patterns.
Incident Response & Digital Forensics
IR playbook execution, evidence collection, forensic timeline analysis, memory forensics, and post-incident reporting following NIST SP 800-61 and SANS PICERL methodology.
collecting-volatile-evidence-from-compromised-host
Collect volatile forensic evidence from a compromised system following order of volatility, preserving memory, network connections, processes, and system state before they are lost.
incident-response-expert
Expert in security incident response, NIST framework, digital forensics, containment strategies, and recovery procedures. Use when the user mentions forensics, NIST, containment, recovery, or cybersecurity, or when the task involves NIST Incident Response Lifecycle, Incident Classification, Incident Response Workflow…