actor-profile
Build a threat actor profile brief from mlab.sh actor intelligence - origin, motivations, targeting, aliases, exploited CVEs, tools and techniques. Use when the user names a threat actor or APT group (APT28, Lazarus, Scattered Spider...), asks who is behind a campaign, or wants to know whether an actor targets their sector or exploits a given CVE.
- License 许可
- MIT
- 最近更新
- 2026-10-22
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- actor-profile
- description
- Build a threat actor profile brief from mlab.sh actor intelligence - origin, motivations, targeting, aliases, exploited CVEs, tools and techniques. Use when the user names a threat actor or APT group (APT28, Lazarus, Scattered Spider...), asks who is behind a campaign, or wants to know whether an actor targets their sector or exploits a given CVE.
03 SKILL.md 正文
Threat Actor Profile
Before interpreting any tool result, read
${CLAUDE_PLUGIN_ROOT}/docs/tool-reference.md: verified output shapes and gotchas that override intuition.
Workflow
1. Resolve the actor
Call search_actors with the name the user gave. Slugs are compound and unguessable (Lazarus is lazarus-group-hidden-cobra-labyrinth-chollima), so never construct one - always resolve via search. The search matches primary names only, NOT aliases; primary names are themselves compound ("Lazarus Group, Hidden Cobra, Labyrinth Chollima") so common names often hit anyway, but vendor codenames ("Zinc", "UNC4899") will not - retry with the best-known primary name. Optionally narrow with origin, motivation or sector when the user's question implies them ("Chinese actors targeting finance").
Take the slug from the best match and call get_actor for the full record.
If several actors plausibly match, list them with one line each and ask which one, unless context makes it obvious.
2. Enrich the CVE angle
get_actor returns the CVEs attributed to the actor. For the most relevant ones (recent, or matching the user's stack if known), call cve_detail to get CVSS, EPSS and KEV status. If the user came in from a CVE ("who exploits CVE-2023-2868?"), start from actors_by_cve instead and profile each returned actor briefly.
3. Brief
## <Primary name> (<slug>)
Also known as: <aliases>
**Origin:** <suspected origin> | **Motivation:** <motivations> | **Active since:** <first seen>
**Targets:** <sectors> in <countries>
### Summary
<2-3 sentences from the profile description, in your own words>
### Tradecraft
<`techniques[]` grouped by ATT&CK tactic with MITRE IDs; `tools[]` split malware vs tools with S-ids>
### Exploited vulnerabilities
| CVE | Product | CVSS | KEV | Why it matters |
### Relevance to you
<only if the user's sector, stack or geography is known from context: a concrete read on exposure>
### Sources
<external references from the record>
Rules
- Attribution is always "suspected"/"attributed", never stated as certain fact. Respect the record's
tlpmarking. actors_by_cvecan return pseudo-actors like "[Unnamed groups: China]": report those as "unattributed activity linked to <origin>", not as a named group.- The
descriptionfield contains{{...}}cross-reference markup: rewrite it, never paste it raw. - Do not pad the profile with general knowledge about the actor from memory; the brief reflects the mlab record, and anything added from elsewhere is labeled as such.
- When comparing actors or answering "who targets X", quote the fields (sectors, motivations) rather than inferring.
04 同仓库更多 Skills
threat-watch
Generate a threat landscape digest from mlab.sh - recent critical/KEV CVEs filtered to a declared technology stack, with actor attribution. Use when the user asks what is new in vulnerabilities, wants a daily/weekly threat brief, asks about recent CVEs for a product, or sets up a recurring watch on their stack.
supply-chain-audit
Full supply-chain audit of a project - postmortem detects malicious code, install hooks and risky dependencies locally, then mlab.sh enriches what it finds (hashes, endpoints, actors, CVEs). Use when the user asks to audit a project's dependencies or supply chain, check a repo for malicious packages, or vet a codebase before adoption or deployment.
smishing-campaign
Analyze a batch of reported SMS/text messages through mlab.sh - score each for smishing, cluster them into campaigns, and extract the shared infrastructure (URLs, callback numbers, sender patterns). Use when the user has multiple reported SMS from users/employees, or investigates an SMS phishing wave. For a single message, phishing-triage does the job.
script-triage
Statically analyze a suspicious shell script through mlab.sh - install.sh, cron payloads, CI steps, curl-pipe-sh one-liners. Flags dangerous constructs (download-piped-to-shell, base64 decoding, reverse shells, persistence, anti-forensics, destructive deletes), extracts every IOC and enriches them. Use when the user pastes shell code and asks if it is safe/malicious, or provides a .sh file to vet before running it.
sbom-export
Generate a CycloneDX SBOM locally with postmortem and push it through mlab.sh vulnerability scanning - for projects or container images where no single lockfile can be pasted. Use when the user asks for an SBOM, needs vuln scanning of a container image or a multi-ecosystem repo, or when sbom-audit lacks a usable lockfile.
sbom-audit
Audit a dependency lockfile or SBOM for known vulnerabilities via mlab.sh, prioritize findings by KEV status and EPSS, and attribute actively exploited CVEs to threat actors. Use when the user provides a lockfile (package-lock.json, yarn.lock, pnpm-lock.yaml, Cargo.lock, requirements.txt, poetry.lock, uv.lock, Pipfile.lock, go.sum, composer.lock, Gemfile.lock, pom.xml, gradle.lockfile, packages.lock.json, pubspec.lock, mix.lock) or a CycloneDX / SPDX SBOM, or asks to check dependencies for vulnerabilities.