SECUpdates
Customization
Before executing, check for user customizations at:
~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/SECUpdates/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
Voice Notification (REQUIRED)
Send this notification BEFORE doing anything else:
curl -s -X POST http://localhost:8888/notify \
-H "Content-Type: application/json" \
-d '{"message": "Checking security updates from sources"}' \
> /dev/null 2>&1 &
SECUpdates Skill
Purpose: Aggregate security news from multiple sources into crisp, ranked updates across three categories.
Sources
| Source | URL | Type |
|---|---|---|
| tl;dr sec | https://tldrsec.com | Newsletter/RSS - comprehensive security roundup |
| No Security | https://no.security | Caleb Sima's security insights |
| Krebs on Security | https://krebsonsecurity.com | Investigative security journalism |
| The Hacker News | https://thehackernews.com | Security news and analysis |
| Schneier on Security | https://schneier.com | Bruce Schneier's security blog |
| Risky Business | https://risky.biz | Security podcast/news |
Custom sources: Add to USER/SKILLCUSTOMIZATIONS/SECUpdates/sources.json
Output Format
Maximum 32 items total across all categories, ranked by importance within each.
# Security Updates
**Generated:** [timestamp]
**Sources Checked:** [list]
**Period:** Since [last check date]
---
## 🔴 Security News (Breaches & Incidents)
*Hacks, breaches, exploits in the wild, incidents*
1. **[Headline]** - [1-2 sentence summary]. [Source]
2. **[Headline]** - [1-2 sentence summary]. [Source]
...
---
## 🔬 Security Research
*New vulnerabilities, CVEs, techniques, papers*
1. **[Title]** - [1-2 sentence summary]. [Source]
2. **[Title]** - [1-2 sentence summary]. [Source]
...
---
## 💡 Security Ideas
*Opinions, strategies, industry trends, career*
1. **[Title]** - [1-2 sentence summary]. [Source]
2. **[Title]** - [1-2 sentence summary]. [Source]
...
---
## 📊 Summary
| Category | Count | Top Item |
|----------|-------|----------|
| News | X | [headline] |
| Research | X | [title] |
| Ideas | X | [title] |
**Total:** X/32 items | **Next check:** Run `/secupdates` anytime
Category Definitions
🔴 Security News (Breaches & Incidents)
- Data breaches and leaks
- Active exploits and attacks
- Ransomware incidents
- State-sponsored attacks
- Major vulnerability exploitations
- Company security incidents
🔬 Security Research
- New CVEs and vulnerabilities
- Security research papers
- New attack techniques
- Tool releases
- Vulnerability disclosures
- Bug bounty findings
💡 Security Ideas
- Industry trends and analysis
- Security strategy and opinions
- Career and hiring trends
- Regulatory and compliance news
- Security culture and practices
- Predictions and forecasts
Ranking Criteria
Within each category, rank items by:
- Impact - How many people/systems affected?
- Recency - How new is this?
- Actionability - Can reader do something about it?
- Novelty - Is this genuinely new information?
State Tracking
State file: State/last-check.json
{
"last_check_timestamp": "2026-01-22T12:00:00.000Z",
"sources": {
"tldrsec": {
"last_hash": "abc123",
"last_checked": "2026-01-22T12:00:00.000Z",
"last_title": "tl;dr sec #XXX"
},
"nosecurity": {
"last_hash": "def456",
"last_checked": "2026-01-22T12:00:00.000Z"
}
}
}
On each run:
- Load last-check.json
- Fetch each source
- Compare content hash to detect new items
- Only include items newer than last check
- Update state file after successful run
Process Flow
Step 1: Check State
# Read last check timestamp
cat State/last-check.json
Step 2: Fetch Sources (Parallel)
Launch parallel agents to fetch each source:
| Agent | Source | Method |
|---|---|---|
| Agent 1 | tldrsec.com | WebFetch latest newsletter |
| Agent 2 | no.security | WebFetch recent posts |
| Agent 3 | krebsonsecurity.com | WebFetch recent articles |
| Agent 4 | thehackernews.com | WebFetch headlines |
| Agent 5 | schneier.com | WebFetch recent posts |
Step 3: Parse & Categorize
For each item found:
- Determine category (News/Research/Ideas)
- Extract headline and 1-2 sentence summary
- Note source
- Assess importance score
Step 4: Rank & Limit
- Sort each category by importance
- Take top items until 32 total
- Distribute reasonably (aim for ~10-12 per category if available)
Step 5: Output & Update State
- Generate formatted output
- Write updated state to last-check.json
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| Update | "security updates", "sec updates", "/secupdates", "what's new in security" | Workflows/Update.md |
Default: Run the Update workflow.
Key Principles
- Crisp - 1-2 sentences per item, no fluff
- Ranked - Most important first within each category
- Categorized - Clear separation of News/Research/Ideas
- Deduplicated - Same story from multiple sources = one entry
- Limited - Max 32 items total, quality over quantity
- Stateful - Track what's been seen, only show new items
Example Output
# Security Updates
**Generated:** 2026-01-22 12:09 PST
**Sources Checked:** tldrsec, no.security, Krebs, THN, Schneier
**Period:** Since 2026-01-20
---
## 🔴 Security News (Breaches & Incidents)
1. **Microsoft Azure Breach Exposes 2M Customer Records** - Misconfigured storage blob allowed unauthorized access to customer data including emails and phone numbers. [Krebs]
2. **LockBit 4.0 Ransomware Hits Healthcare Chain** - 15 hospitals affected, patient data encrypted, $10M ransom demanded. [THN]
3. **Ivanti VPN Zero-Day Actively Exploited** - CVE-2026-XXXX being used by Chinese APT groups against government targets. [tldrsec]
---
## 🔬 Security Research
1. **New Spectre Variant Bypasses All Mitigations** - Researchers demonstrate "Spectre-NG" affecting Intel and AMD processors, no patch available. [tldrsec]
2. **OAuth Token Theft via Browser Extension** - Novel technique allows stealing tokens from any site using malicious extension. [no.security]
3. **SSRF in AWS IMDSv2** - Bypass discovered in metadata service protections. [tldrsec]
---
## 💡 Security Ideas
1. **The Death of Perimeter Security** - Caleb Sima argues zero-trust is no longer optional after recent breaches. [no.security]
2. **CISO Burnout at All-Time High** - Survey shows 70% considering leaving the field within 2 years. [tldrsec]
3. **AI-Generated Phishing Now Indistinguishable** - Schneier on the implications of LLM-powered social engineering. [Schneier]
---
## 📊 Summary
| Category | Count | Top Item |
|----------|-------|----------|
| News | 3 | Microsoft Azure Breach |
| Research | 3 | New Spectre Variant |
| Ideas | 3 | Death of Perimeter Security |
**Total:** 9/32 items | **Next check:** Run `/secupdates` anytime
Anti-Patterns
| ❌ Bad | ✅ Good |
|---|---|
| Long paragraph summaries | 1-2 crisp sentences |
| "Read more at..." | Summary + source attribution |
| Unranked list dumps | Importance-ordered items |
| 50+ items | Max 32, quality curated |
| Mixing categories | Clear News/Research/Ideas separation |
| Old news mixed with new | Only items since last check |
More from danielmiessler/personal_ai_infrastructure
osint
Structured OSINT investigations — people lookup, company intel, investment due diligence, entity/threat intel, domain recon, organization research using public sources with ethical authorization framework. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate, company lookup, domain lookup, entity lookup, organization lookup, threat intel, discover OSINT sources.
259firstprinciples
Physics-based reasoning framework (Musk/Elon methodology) that deconstructs problems to irreducible fundamental truths rather than reasoning by analogy. Three-step structure: DECONSTRUCT (break to constituent parts and actual values), CHALLENGE (classify every element as hard constraint / soft constraint / unvalidated assumption — only physics is truly immutable), RECONSTRUCT (build optimal solution from fundamentals alone, ignoring inherited form). Outputs: constituent-parts breakdown, constraint classification table, and reconstructed solution with key insight. Three workflows: Deconstruct.md, Challenge.md, Reconstruct.md. Integrates with RedTeam (attack assumptions before deploying adversarial agents), Security (decompose threat model), Architecture (challenge design constraints), and Pentesters (decompose assumed security boundaries). Other skills invoke via: Challenge on all stated constraints → classify as hard/soft/assumption. Cross-domain synthesis: solutions from unrelated fields often apply once the fundamental truths are exposed. NOT FOR incident investigation and causal chains (use RootCauseAnalysis). NOT FOR structural feedback loops (use SystemsThinking). USE WHEN first principles, fundamental truths, challenge assumptions, is this a real constraint, rebuild from scratch, what are we actually paying for, what is this really made of, start over, physics first, question everything, reasoning by analogy, is this really necessary.
160documents
Read, write, convert, and analyze documents — routes to PDF, DOCX, XLSX, PPTX sub-skills for creation, editing, extraction, and format conversion. USE WHEN document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form, tracked changes, redlining.
114council
Multi-agent collaborative debate that produces visible round-by-round transcripts with genuine intellectual friction. All council members are custom-composed via ComposeAgent (Agents skill) with domain expertise, unique voice, and personality tailored to the specific topic — never built-in generic types. ComposeAgent invoked as: bun run ~/.claude/skills/Agents/Tools/ComposeAgent.ts. Two workflows: DEBATE (3 rounds, full transcript + synthesis, parallel execution within rounds, 40-90 seconds total) and QUICK (1 round, fast perspective check). Context files: CouncilMembers.md (agent composition instructions), RoundStructure.md (three-round structure and timing), OutputFormat.md (transcript format templates). Agents are designed per debate topic to create real disagreement; 4-6 well-composed agents outperform 12 generic ones. Council is collaborative-adversarial (debate to find best path); for pure adversarial attack on an idea, use RedTeam instead. NOT FOR parallel task execution across agents (use Delegation skill). USE WHEN council, debate, multiple perspectives, weigh options, deliberate, get different views, multi-agent discussion, what would experts say, is there consensus, pros and cons from multiple angles.
112privateinvestigator
Ethical people-finding using 15 parallel research agents (45 search threads) across public records, social media, reverse lookups. Public data only, no pretexting. USE WHEN find person, locate, reconnect, people search, skip trace, reverse lookup, social media search, public records search, verify identity.
112redteam
Military-grade adversarial analysis that deploys 32 parallel expert agents (engineers, architects, pentesters, interns) to stress-test ideas, strategies, and plans — not systems or infrastructure. Two workflows: ParallelAnalysis (5-phase: decompose into 24 atomic claims → 32-agent parallel attack → synthesis → steelman → counter-argument, each 8 points) and AdversarialValidation (competing proposals synthesized into best solution). Context files: Philosophy.md (core principles, success criteria, agent types), Integration.md (how to combine with FirstPrinciples, Council, and other skills; output format). Targets arguments, not network vulnerabilities. Findings ranked by severity; goal is to strengthen, not destroy — weaknesses delivered with remediation paths. Collaborates with FirstPrinciples (decompose assumptions before attacking) and Council (Council debates to find paths; RedTeam attacks whatever survives). Also invoked internally by Ideate (TEST phase) and WorldThreatModel (horizon stress-testing). NOT FOR AI instruction set auditing (use BitterPillEngineering). NOT FOR network/system vulnerability testing (use a security assessment skill). USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, what could go wrong, strongest objection, adversarial validation, battle of bots.
112