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 agentmods add skills/thejefflarson/soundcheck/ssrfnpx skills add thejefflarson/soundcheck --skill ssrfgit clone --depth 1 https://github.com/thejefflarson/soundcheckWhat 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 | $0.00064 | $0.00912 |
| Opus 5 | $0.00032 | $0.00456 |
| Sonnet 5 | $0.00013 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade C, and why
ssrf scanned grade C with 1 finding 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 2d 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 endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
metadata APIs (169.254.169.254), and access to services behind firewalls. How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SSRF Security Check (A10:2025 / API7:2023)
What this checks
Protects against Server-Side Request Forgery where an attacker tricks the server into making requests to internal services, cloud metadata endpoints, or arbitrary external hosts. Exploitation leads to internal network scanning, credential theft from cloud metadata APIs (169.254.169.254), and access to services behind firewalls.
Vulnerable patterns
- Outbound HTTP fetch where the URL, host, or scheme comes from request input with no validation
- Webhook callback or URL-preview feature that follows whatever the caller supplies
- URL-fetch APIs that follow redirects by default, letting an allowlisted host 302 to an internal IP
- Hostname-only allowlists that do not also check the resolved IP — vulnerable to DNS rebinding
Fix immediately
Flag the vulnerable code, explain the risk, and suggest a fix establishing these properties. Proxy, webhook, and URL-preview features are the highest-risk shapes — the scheme/host/IP/redirect checks must actually run at the call site before the outbound request; a comment saying "URL should be validated" satisfies nothing if the next line still fetches the raw URL. Translate to the language and HTTP client of the audited file — use that stack's documented URL parser, DNS resolver, and redirect controls.
- Scheme is restricted to
https(andhttponly for trusted internal use). Rejectfile:,gopher:,ftp:,dict:, and other schemes that SSRF toolkits exploit. - Host is checked against an allowlist, and the resolved IP is checked against a blocklist covering private, loopback, and link-local ranges — IPv4
10.0.0.0/8,172.16.0.0/12,192.168.0.0/16,127.0.0.0/8,169.254.0.0/16and IPv6::1/128,fc00::/7,fe80::/10. Resolve-then-check defeats DNS rebinding: an allowlisted hostname can still resolve to169.254.169.254. Language-idiomatic checks that cover the same ranges are equivalent to explicit CIDR comparisons. - Redirects are disabled, or each redirect target is re-validated against the same allowlist. A lone allowlisted host can still 302 to an internal IP.
- The check actually runs. A blocklist declared and never evaluated does not satisfy any of the above — the comparison must be present at the call site, before the outbound request.
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.
- 2d ago First seen · 53 lines · 64 tokens per session scan C 17ea2c6aa438
ssrf is a skill published in the GitHub repository thejefflarson/soundcheck (20 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 912 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
make-skill
Use this skill when sedimenting a session into a reusable workspace skill. Triggers when the user wants to turn the current conversation, workflow, or troubleshooting path into a SKILL.md. Phrases like 'turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this', and any /make-skill…
make-skill
用于把当前会话沉淀为可复用的 workspace skill。当用户希望把当前对话、工作流或排错路径写成 SKILL.md 时触发。触发表达包括「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」以及任何 /make-skill 调用。.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
docx
当用户需要创建、读取、编辑或处理 Word 文档（.docx）时，使用此技能。触发场景包括提到“Word 文档”、“.docx”，或要求生成带目录、标题、页码、信头等格式的专业文档；也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注，以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物，也应使用此技能。不要用于 PDF、电子表格、Google Docs，或与文档生成无关的一般编程任务。.
multi_agent_collaboration
Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use qwenpaw agents chat for two-way communication with replies.