Abnormal Security Messages SKILL.md skillA
Abnormal Security Messages from wyre-ai/msp-claude-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wyre-ai/msp-claude-plugins/Abnormal Security Messages@git:20260806.ad583a2Pins git:20260806.ad583a2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wyre-ai/msp-claude-plugins
- Path
msp-claude-plugins/abnormal/abnormal-security/skills/messages/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260806.ad583a2, committed Aug 6, 2026
- First version recorded
- Apr 5, 2026
- Size
- 10,198 bytes
- Repository stars
- 52
- License
- Apache-2.0
Abnormal Security message analysis: message retrieval, email header inspection, attachments, sender reputation, delivery context, and SPF/DKIM/DMARC authentication results.
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
# Abnormal Security Message Analysis ## Overview Abnormal Security provides deep message analysis capabilities beyond basic threat detection. This skill covers message retrieval, header inspection, attachment analysis, sender authentication results, and delivery context. Use it when performing forensic analysis of specific emails or investigating delivery patterns. ## Anti-triggers - **Where a message went, or why it never arrived** — Abnormal sees messages only as evidence attached to a detected threat. It has no delivery pipeline, no queue, and no bounce record, so "trace this email" questions belong to the gateway: use `Mimecast Message Tracking`. - **Removing the message from inboxes, or putting it back** — that is the remediation surface; use `Abnormal Security Threats`. - **Inspecting a message a gateway is holding** — everything Abnormal can show was already delivered. Pre-delivery holds are `SpamTitan Quarantine` or `Proofpoint Quarantine`. ## Message Field Reference These are **response** fields describing what Abnormal reports about a message. They are not tool parameters — the only parameters the message …
Read the whole file at its exact version.
How to install
mdr add wyre-ai/msp-claude-plugins/Abnormal Security Messages@sha256:56467d63fe749706The line at the top of this page pins the label git:20260806.ad583a2, 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_sbryduvexxtiliqs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 5, 2026 and Aug 6, 2026, about one every 31 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260806.ad583a2 latest | 2026-08-06 | ad583a2 | 10,198 B | A | view · diff |
| git:20260804.e135c70 | 2026-08-04 | e135c70 | 8,492 B | A | view · diff |
| git:20260728.b7e78fc | 2026-07-28 | b7e78fc | 7,875 B | A | view · diff |
| git:20260713.1fbd3f3 | 2026-07-13 | 1fbd3f3 | 8,120 B | A | view · diff |
| git:20260405.09d00fc | 2026-04-05 | 09d00fc | 8,143 B | A | 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 (10198 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
wyre-ai/msp-claude-plugins · 52 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sbryduvexxtiliqs GET https://markdownregistry.com/api/v1/resolve?ref=wyre-ai/msp-claude-plugins/Abnormal Security Messages GET https://markdownregistry.com/api/v1/blob/56467d63fe749706e5aebb8f0e56cb226f62c6a0937b547c7160fc216cb7bfb9
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.