AGENT SKILL

phishing-triage

Analyze a suspicious email, SMS or message for phishing/smishing using mlab.sh - sender address reputation, domain spoofability (SPF/DKIM/DMARC), embedded URL analysis, callback phone numbers and smishing scoring. Use when the user pastes a suspicious message, reports a phishing attempt, or asks whether an email/SMS/link is legit.

License 许可
MIT
最近更新
2026-10-22
Stars
★ 1
Forks
0

01 前言 Front Matter

name
phishing-triage
description
Analyze a suspicious email, SMS or message for phishing/smishing using mlab.sh - sender address reputation, domain spoofability (SPF/DKIM/DMARC), embedded URL analysis, callback phone numbers and smishing scoring. Use when the user pastes a suspicious message, reports a phishing attempt, or asks whether an email/SMS/link is legit.

03 SKILL.md 正文

Phishing / Smishing Triage

Before interpreting any tool result, read ${CLAUDE_PLUGIN_ROOT}/docs/tool-reference.md: verified output shapes and gotchas that override intuition.

Workflow

Decompose the message into its indicators, score each, then give one combined verdict.

1. The message body (SMS or short message)

For an SMS or text-style message, run smishing_risk on the full RAW body - the IOC extractor does not parse defanged text, so refang (hxxp -> http, [.] -> .) if you only have a defanged copy. Pass country matching the user's locale pack (default fr). Use the returned iocs[] as your indicator list rather than parsing by hand, and re-defang everything for the report.

2. The sender

  • Email address → scan_email. Key signals: disposable/role mailbox type, and the domain's spoofability verdict (SPF/DKIM/DMARC). A spoofable domain means the From header proves nothing.
  • Phone number → scan_phone. VoIP line type and country/operator mismatches with the claimed brand are strong signals.

3. Embedded links

For each URL, run scan_url (static). Highlights to check: punycode/Unicode host confusion, credentials-in-URL, IP-literal hosts, dangerous file extensions, known shorteners, embedded redirect targets, and the host's registration age when a previous domain scan exists.

Only set resolve: true on a shortener when the destination is needed for the verdict, and note in the report that the link was followed. If the sender domain itself looks central to the case and is unscanned, offer to run start_domain_scan (it consumes quota).

4. Verdict

## Verdict: <phishing | suspicious | likely legitimate> (confidence: <low/med/high>)

**One-line summary for the end user:** <plain-language, no jargon>

### Signals
| Element | Finding | Weight |
<sender, each link, body score - with the tool-reported reasons>

### What to do
<for an end user: don't click / report to X / delete. For a SOC: block indicators, search mail logs for the sender/URL pattern>

### Extracted IOCs
<clean list, ready to paste into a blocklist or hunt>

Rules

  • Quote the scoring reasons the tools return; never present a bare number as the argument.
  • A low smishing score with conclusive: false is not a clean bill; say what could not be checked.
  • Brand impersonation is a judgment call: state which brand the message imitates and which signals support that.
  • Never advise the user to interact with the message (reply, call the number, open the link) to "test" it.

04 同仓库更多 Skills

mlab-sh
mlab-sh/mlab-claude

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.

★ 1
mlab-sh
mlab-sh/mlab-claude

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.

★ 1
mlab-sh
mlab-sh/mlab-claude

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.

★ 1
mlab-sh
mlab-sh/mlab-claude

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.

★ 1
mlab-sh
mlab-sh/mlab-claude

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.

★ 1
mlab-sh
mlab-sh/mlab-claude

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.

★ 1