hypothesis-driven-hunting SKILL.md skillA
hypothesis-driven-hunting from annatchijova/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add annatchijova/skills/hypothesis-driven-hunting@git:20260825.8500180Pins git:20260825.8500180 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- annatchijova/skills
- Path
hypothesis-driven-hunting/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260825.8500180, committed Aug 25, 2026
- Size
- 7,403 bytes
- Repository stars
- 9
- License
- a license file GitHub does not identify
Run a threat hunt as a falsifiable hypothesis about adversary behavior, not a keyword sweep — state before you query what you expect to see if it is true, what would refute it, and what "found nothing" actually proves, which is almost always far less than the hunter wants to claim. Use whenever someone is threat hunting or proposing to: "let's hunt for lateral movement", "go look for signs of compromise", "hunt for persistence", "we should proactively search for X", "did we find anything…
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
# Hypothesis-Driven Hunting A threat hunt is a claim about the world — "an actor performed *this behavior* in *this environment*, and if so, *these artifacts* exist in *these logs*" — subjected to a test that could refute it. It is not running a block of IOC searches and seeing what lights up. The difference is the whole discipline: a hunt with no stated refutation condition cannot fail, and a search that cannot fail has not learned anything when it returns empty. It has produced the *feeling* of coverage, which is worse than no hunt, because someone will now report the environment as clean. Two failure modes, and the second is the quiet, dangerous one: - **Grep-for-evil.** A pile of IOC queries with no hypothesis behind them. A hit is a "maybe" you cannot interpret (the IOC is stale, shared, or benign), and a miss means nothing at all — you did not define what a miss would rule out. - **Absence-as-proof.** Treating "the hunt found no evidence" as "there is no adversary." A null result is bounded entirely by the data you queried, its retention, and its coverage. "Not present in these logs, for this window, at this fidelity" is the honest …
Read the whole file at its exact version.
How to install
mdr add annatchijova/skills/hypothesis-driven-hunting@sha256:ac09186730f28006The line at the top of this page pins the label git:20260825.8500180, 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_z6nyztslffm3gkxe)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 25, 2026.
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 (7403 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
annatchijova/skills · 9 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_z6nyztslffm3gkxe GET https://markdownregistry.com/api/v1/resolve?ref=annatchijova/skills/hypothesis-driven-hunting GET https://markdownregistry.com/api/v1/blob/ac09186730f280061259a5916306999db4cbe2a14a05f91a7def3821671d2e09
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.