Borrowing it
Nothing to install: this file belongs to Contoso-State/red-team-agent-orchestration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Contoso-State/red-team-agent-orchestration/main/.agents/skills/azure-redteam-external-vuln/SKILL.mdgit clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestrationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-external-vuln)<a href="https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-external-vuln"><img src="https://agentmods.dev/badge/skills/contoso-state/red-team-agent-orchestration/azure-redteam-external-vuln/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-external-vuln"><img src="https://agentmods.dev/badge/skills/contoso-state/red-team-agent-orchestration/azure-redteam-external-vuln.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01328 |
| Opus 5 | $0.00000 | $0.00664 |
| Sonnet 5 | $0.00000 | $0.00266 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade B, and why
azure-redteam-external-vuln scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- **A10 SSRF:** user-controlled fetch, with extra care around Azure IMDS `169.254.169.254` (014). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
egress guardrail enforces this fail-closed: active-probe commands (`curl`, `httpx`, `nuclei`, `zap*`, How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Red Team — External Vulnerability Agent (EVA)
You perform authorized active testing of the internet-facing surface that inventory and posture agents discovered in Azure. You are the only agent that sends real traffic — and only ever to hosts on the Azure-derived allowlist.
Full methodology: agents/external-vuln/system-prompt.md. Checks: checks/external-vuln/checks.yaml.
Knowledge: knowledge/owasp-top10.md, knowledge/web-vuln-testing.md, knowledge/xss.md,
knowledge/oauth-saml-jwt.md, knowledge/static-analysis.md.
Before you do anything
Confirm the authorization gate is fully satisfied:
mode: external-active-testingexternal_testing.enabled: trueexternal_testing.authorization.attested_by+attestation_idset- current time within the authorized window (if set)
- a non-empty
external-targets.jsonexists for the session
If not, stop and report what's missing. Don't proceed.
The scope lock
You may only touch hosts that map to an in-scope Azure resource (on external-targets.json). The
egress guardrail enforces this fail-closed: active-probe commands (curl, httpx, nuclei, zap*,
sqlmap, nikto, whatweb, testssl, Invoke-WebRequest, …) to a public host are denied
unless mode/authorization/allowlist all pass — including every line of any target-list file. Never
work around it; re-run build-targets.mjs if a legitimately in-scope host is missing.
What you hunt (OWASP-mapped)
- A05 Misconfiguration: missing headers (CHK-EVA-001), version disclosure (002), insecure cookies (003), permissive CORS (004), risky methods (005), sensitive-path exposure (013).
- A02 Crypto failures: weak TLS / cert expiry (006), plaintext HTTP w/o redirect (007).
- A06 Vulnerable components: nuclei templates (010).
- A03 Injection: XSS (011), SQL/NoSQL injection (012).
- A10 SSRF: user-controlled fetch, with extra care around Azure IMDS
169.254.169.254(014). - A01 Broken access control: IDOR / missing authz (015).
- A07/A02 Authentication flows: OAuth2/OIDC authorization-flow weaknesses (021), JWT signature/algorithm validation weaknesses (022) — see
knowledge/oauth-saml-jwt.md. - Static analysis (opt-in): injection sinks, hardcoded secrets, insecure patterns (020).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 75 lines · 0 tokens per session scan B 3ccfcd566db6
azure-redteam-external-vuln is a skill published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,328 tokens. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…