defense-strategies SKILL.md skillA
defense-strategies from hermeticormus/libresecops-claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hermeticormus/libresecops-claude-code/defense-strategies@git:20260930.71a2663Pins git:20260930.71a2663 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hermeticormus/libresecops-claude-code
- Path
plugins/social-engineering-defense/skills/defense-strategies/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260930.71a2663, committed Sep 30, 2026
- First version recorded
- Feb 25, 2026
- Size
- 10,147 bytes
- Repository stars
- 4
- License
- MIT
Technical and human controls for preventing, detecting, and responding to social engineering across email, phone, SMS, and physical channels, including SPF, DKIM, DMARC, payment verification callbacks, dual authorization, and response procedures. Use when designing layered defenses or responding to a phishing or BEC incident.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Defense Strategies > Technical and human defense controls for preventing, detecting, and responding to social engineering attacks across all channels. ## Knowledge Base ### Defense-in-Depth Model for Social Engineering Social engineering defense requires layered controls because no single control stops all attacks. The layers work together: ``` Layer 1: Perimeter (prevent delivery) Email filtering, URL filtering, phone call screening Layer 2: Technical enforcement (prevent exploitation) MFA, conditional access, email authentication (DMARC) Layer 3: Human detection (recognize attacks) Awareness training, verification procedures, reporting culture Layer 4: Process controls (prevent impact) Dual authorization for financial transfers, callback verification Layer 5: Response (minimize damage) Incident response, account lockout, forensic analysis ``` ### Technical Controls **Email Authentication (prevent domain spoofing)** | Control | Purpose | Implementation | |---------|---------|---------------| | SPF | Authorize sending servers | DNS TXT record listing authorized IPs | | DKIM | Cryptographic email signing | Public key in DNS, signing by mail server | …
Read the whole file at its exact version.
How to install
mdr add hermeticormus/libresecops-claude-code/defense-strategies@sha256:b49bbc183cdc9927The line at the top of this page pins the label git:20260930.71a2663, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uifhvgckpqnu2obf)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Feb 25, 2026 and Sep 30, 2026, about one every 218 days. Its first recorded version is graded C and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260930.71a2663 latest | 2026-09-30 | 71a2663 | 10,147 B | A | view · diff |
| git:20260225.9d494ed | 2026-02-25 | 9d494ed | 9,768 B | C | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10147 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hermeticormus/libresecops-claude-code · 4 stars · license MIT · pushed 2026-10-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uifhvgckpqnu2obf GET https://markdownregistry.com/api/v1/resolve?ref=hermeticormus/libresecops-claude-code/defense-strategies GET https://markdownregistry.com/api/v1/blob/b49bbc183cdc992750b2f0e43e91a9a88d43013bd020c3a2a90e846004af7f67
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.