Install
$ agentstack add skill-arttapon1-defensive-soc-skills-ir-report-builder ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
IR Report Builder
Turn raw logs, alerts, and incident notes into a defensible investigation: a reconstructed timeline, a response plan mapped to a recognized methodology, and two audiences' worth of reporting — deep technical detail for responders and a tight executive summary for leadership.
> Defensive use. This skill is for authorized incident response on systems you own or are engaged to defend. Preserve evidence integrity; never alter source logs — work on copies.
Activation triggers
Use this skill when the user:
- Provides logs (firewall, EDR, auth, web, proxy, DNS, cloud audit) and asks "what happened."
- Asks for an incident report, post-incident review, or executive summary.
- Needs an IR plan, containment/eradication/recovery steps, or a lessons-learned writeup.
- Wants a timeline or root-cause analysis from scattered data.
Methodology
Follow NIST SP 800-61r2 phases, cross-referenced with SANS PICERL: Preparation → Detection & Analysis → Containment → Eradication → Recovery → Post-Incident. Map adversary behavior to MITRE ATT&CK technique IDs wherever the evidence supports it.
Workflow
- Intake & scope. Ask for (or infer from provided data): incident type, affected assets, detection time, data sources available, and business criticality. Confirm the reporting window and time zone. Never assume authorization — confirm it.
- Normalize the evidence. Identify each log source and its format. Use
scripts/log_timeline.pyto parse common formats (RFC3164/RFC5424 syslog, JSON lines, CSV, CEF, Apache/Nginx access, FortiGate & appliance key-value/logfmt, and AWS CloudTrail JSON) into a single normalized, timezone-aligned event list. Keep a hash of every source file for chain of custody.
- Reconstruct the timeline. Order events chronologically. Flag the initial access, first malicious action, lateral movement, privilege escalation, impact, and last observed activity. Note gaps in logging as gaps, not as absence of activity.
- Analyze.
- Extract IOCs (IPs, domains, hashes, user accounts, file paths) into
resources/ioc-extract.mdshape. - Map each observed step to a MITRE ATT&CK technique.
- Determine root cause and the exploited weakness.
- Assess blast radius: what was accessed, exfiltrated, or altered.
- Build the IR plan. Produce concrete Containment / Eradication / Recovery actions with owners and priority. Distinguish already done vs recommended next.
- Write two deliverables.
- Technical report → fill
templates/ir-report-template.md. Dense, evidence-cited, reproducible. - Executive summary → fill
templates/exec-summary-template.md. One page, business-impact-first, no jargon. Answer: what happened, what's the impact, is it contained, what do we need from leadership.
- Quality gate. Every claim in the report must cite an evidence line (timestamp + source). Mark anything inferred as assessed with [high/medium/low] confidence. List logging/visibility gaps explicitly.
Output format
- Technical report: Markdown, sectioned per the template, with an appendix of raw evidence excerpts and IOC tables.
- Executive summary: single page, leads with impact and status. Use a severity label (Critical/High/Medium/Low) and a one-line "bottom line up front."
Handoffs
- IOCs and observed techniques → feed into
siem-detection-engineerto build detections that would have caught this earlier. - Containment actions that should be automated → feed into
soar-playbook-builder.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: arttapon1
- Source: arttapon1/defensive-soc-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.