Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnboundCompute/security-agent-skills --skill exploiting-ssrf-to-cloud-metadatagit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/exploiting-ssrf-to-cloud-metadata)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/exploiting-ssrf-to-cloud-metadata"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/exploiting-ssrf-to-cloud-metadata/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/unboundcompute/security-agent-skills/exploiting-ssrf-to-cloud-metadata"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/exploiting-ssrf-to-cloud-metadata.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 | $0.00113 | $0.01553 |
| Opus 5.5 | $0.00045 | $0.00621 |
| Sonnet 5.5 | $0.00023 | $0.00311 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
exploiting-ssrf-to-cloud-metadata scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploiting SSRF to cloud metadata: reach is what makes it critical
A server that fetches a URL an attacker can influence is only dangerous if that fetch reaches something worth reaching. The highest-value target in a cloud environment is the instance metadata service, a link-local endpoint that returns the workload's credentials to anything that can make it a request. Turning an SSRF lead into a real finding means proving the request is steerable, reaches an internal target, survives the filters, and returns something that matters, usually a credential.
When to use
- A feature makes a server-side request to a URL, host, or address the user influences (a webhook, importer, link preview, URL parameter).
- You are triaging an SSRF lead and need to know its real impact.
- You are assessing exposure of a cloud workload's metadata and credentials.
Scope check
Test only infrastructure you are authorized to assess. Retrieve credentials solely from your own instances and revoke them after. If you can't name the authorization, stop.
The loop
-
Confirm the fetch is attacker-steered. Find the feature that makes a server-side request and confirm the destination, or part of it, comes from your input. If you cannot influence where the request goes, there is no SSRF; if you can, establish exactly which part (scheme, host, path, port).
-
Establish internal reach. Point the request at addresses the server should never fetch on your behalf: loopback, link-local, and internal ranges, and internal hostnames. Use an out-of-band listener to confirm the server actually made the request when the response is not reflected. Reaching an internal address at all is the core of the primitive.
-
Aim at the metadata endpoint. Direct the fetch at the cloud instance metadata address and its credential path. If the environment does not require the hardened, header-bound request flow, or the feature can be made to supply the required header, the endpoint returns the instance role's temporary credentials. Retrieving those is the critical outcome.
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.
- 1mo ago First seen · 130 lines · 113 tokens per session scan A f0631b4a006d
exploiting-ssrf-to-cloud-metadata is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,553 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.