dual-use-behavior-adjudication SKILL.md skillA
dual-use-behavior-adjudication 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/dual-use-behavior-adjudication@git:20260825.a84759bPins git:20260825.a84759b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- annatchijova/skills
- Path
dual-use-behavior-adjudication/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260825.a84759b, committed Aug 25, 2026
- Size
- 12,929 bytes
- Repository stars
- 9
- License
- a license file GitHub does not identify
Decide whether observed activity is malicious when the tool, command, or API call is itself legitimate — the living-off-the-land problem, where the artifact is identical for the admin and the intruder and the verdict lives entirely in context. Use whenever you must call a signal benign or malicious and the signal alone cannot settle it: PowerShell/WMI/PsExec/certutil/rundll32 execution, a valid credential used from a new location, an `AssumeRole` or `iam:PassRole` that is in-policy, RDP/SSH…
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
# Dual-Use Behavior Adjudication
`certutil` downloads a file. That is its job. It is also how an intruder without
`curl` pulls down a payload. The bytes on the wire, the process name, the command
line, the exit code — identical in both cases. **The artifact does not contain the
verdict.** The verdict lives in who ran it, from where, in what sequence, against
what baseline, next to what else. Adjudicate the artifact and you will be wrong in
both directions: you will wave the intruder through because the tool is "legit,"
and you will flag the sysadmin because the tool is "suspicious."
This skill is the epistemic layer above the entire `detecting-*` / `hunting-*`
family. Those procedures tell you a signal *fired*. This one tells you what the
firing is *worth* — and refuses to let a legitimate tool name settle the question
in either direction.
Two failure modes, symmetric and both fatal:
- **False MALICE.** You escalate the administrator. You burn a day of a real
person's time, you erode every future alert's credibility ("the SOC cries wolf"),
and you train the org to click *dismiss* — which is how the real one gets missed.
…Read the whole file at its exact version.
How to install
mdr add annatchijova/skills/dual-use-behavior-adjudication@sha256:4ccbdd8434270b9fThe line at the top of this page pins the label git:20260825.a84759b, 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_vmnb2jd4cd5s5van)
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 (12929 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_vmnb2jd4cd5s5van GET https://markdownregistry.com/api/v1/resolve?ref=annatchijova/skills/dual-use-behavior-adjudication GET https://markdownregistry.com/api/v1/blob/4ccbdd8434270b9f3bee4c2ded1835c80f3a8bd634c588c08f0ce64cfcd74a94
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.