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 mapping-attack-surfacegit 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/mapping-attack-surface)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/mapping-attack-surface"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/mapping-attack-surface/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/mapping-attack-surface"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/mapping-attack-surface.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 | $0.00111 | $0.01363 |
| Opus 5.5 | $0.00044 | $0.00545 |
| Sonnet 5.5 | $0.00022 | $0.00273 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
mapping-attack-surface 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapping attack surface (black-box)
You can't test what you haven't found, and you'll waste the engagement testing low-value surface first. Recon is the discipline of turning "here's a URL" into a prioritized inventory of everything that takes input, ordered by where bugs live. This skill is the front of the black-box workflow; per-class hunting skills act on its output.
Scope gate - before anything else
Establish and write down scope first, and check every action against it:
- Record the authorization: which hosts/domains/apps are in scope, which are explicitly out, the rules (rate limits, no-DoS, no social engineering, test- account only), and the reporting channel. Keep it where you'll re-read it.
- Check every request against scope before sending it. A wildcard in a program's scope is not permission to hit a third party's system that happens to be reachable.
- Passive before active; low-impact before high. Prefer observation over probing until you've confirmed a target is in scope and the action is allowed.
- Never run destructive or state-changing actions (delete, mass-write, account takeover attempts) without explicit authorization for them.
If you can't point to the authorization for a host or an action, it's out of scope. Stop and confirm.
The recon loop
-
Enumerate hosts. From the in-scope roots: subdomains, related domains, and the apps behind them. Distinguish the origin from CDN/WAF front - testing a CDN edge as if it were the origin yields noise.
-
Fingerprint the stack. Server, framework, language, CMS, reverse proxy, auth provider, cloud. The stack tells you which bug classes are plausible and which default misconfigurations to check.
-
Enumerate endpoints and parameters. Walk the app as an authenticated user (with an in-scope test account), capture the real traffic, and pull the API surface from it. Add documented surface (OpenAPI/GraphQL introspection, JS bundles that reveal routes and params). Most surface is not what you clicked
- it's referenced in client code and specs.
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 · 115 lines · 111 tokens per session scan A ea403f3f2401
mapping-attack-surface is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,363 once invoked, about $0.0004 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.