ultrasafe-web-api-attacker

ultrasafe-web-api-attacker is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 169 tokens per session (7,178 once invoked), scanned A, original, Apache-2.0.

A simulated security tester for websites and web APIs, using common attack perspectives such as SQL injection, cross-site scripting, and authentication bypass.

In plain words
What is it for?
It is used during the Ultrasafe security review process to report possible findings involving API contracts, access control, input handling, requests to other services, and redirects.
Why use it?
It helps identify security weaknesses in web applications and APIs before release by checking how an attacker might misuse them.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions AGENTS.md.

Part of the ultrasafe plugin — 8 skills shipped together

Good fit It is used during the Ultrasafe security review process to report possible findings involving API contracts, access control, input handling, requests to other services, and redirects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/ultrasafe-web-api-attacker
Install

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.

Any agent
npx skills add SoliEstre/EstreGenesis --skill ultrasafe-web-api-attacker
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install ultrasafe, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for ultrasafe-web-api-attacker

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-web-api-attacker/github.svg)](https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-web-api-attacker)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-web-api-attacker"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-web-api-attacker/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.

agentmods 80×15 button for ultrasafe-web-api-attacker

Your own site · 80×15
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ultrasafe-web-api-attacker"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ultrasafe-web-api-attacker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,178 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00169 $0.07178
Opus 5 $0.00084 $0.03589
Sonnet 5 $0.00034 $0.01436
Haiku 4.5 $0.00017 $0.00718

Measured 12d ago against content hash b94660bbfd75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultrasafe-web-api-attacker scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `Bash` — `git log` / `cat package.json` / `npm ls` / `pip list` 등 read-only 명령 한정. **외부 endpoint 호출 금지** (curl / wget / 임의 HTTP).
plugins/ultrasafe/skills/ultrasafe-web-api-attacker/SKILL.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web/API Attacker — Ultrasafe Attacker Skill (v0.2.0)

Role: Agent 2 of the 8-agent Ultrasafe fan-out — Web/API/infra (WAI) attacker perspective. Tone: web-sec-focused (OWASP × MITRE ATT&CK dual taxonomy 표현, CVSS v4 + EPSS + KEV trump 의 priority 수사). Output: ULTRASAFE_FINDING intent emit per finding + attack_path_graph_candidate (v0.2.0 flat list, v0.3+ node/edge promotion). Mode: advisoryvalue.advisory: true 항상 마킹. publish 차단 안 함 (v0.3+ blocking mode 의 wire shape 만 mirror).

본 skill 은 Ultrasafe.md §2.1.2 + §15.2 의 WAI agent role 을 model-invoked skill 로 구현해요. 8-agent fan-out (§15) 의 한 attacker — 본 시각으로 simulated penetration test 수행, finding 을 ULTRASAFE_FINDING A2A intent 로 emit.


§1 When to invoke

본 skill 은 다음 5 trigger 중 하나에서 자동 dispatch 돼요:

  1. Ultrasafe fan-out 의 axis-set 매칭ultrasafe_run_fanout MCP tool (Ultrasafe.md §16.1) 호출 시 axis-set 에 usf-web-sast-dast 또는 usf-web-infra 포함. 8-agent parallel dispatch (Superscalar Workflow fan-out) 의 한 lane.
  2. PreToolUse hook triggerultrasafe-trigger.cjs (§17 + plugins/ultrasafe/hooks/) 가 publish-equivalent command 감지: npm publish / pip upload / cargo publish / git push --tags to public remote / gh release create / docker push / helm push. advisory mode 에서는 report-only emit (차단 안 함).
  3. Inbound A2A SECURITY_DISCLOSURE_INTAKE — 외부 disclosure 수용 시 (Constellation §13.16.5 신규 intent), web-sec category 분류된 disclosure 는 본 attacker 에게 routing → 재현 + cross-axis confirmation.
  4. Iteration boundary re-dispatchULTRASAFE_ITERATION_BOUNDARY emit 후 다음 iteration 진입 시, prior_findings_set 의 regression / persistent 항목이 web-sec category 라면 재시도.
  5. 명시적 user invoke/ultrasafe-web-api-attacker slash 또는 "OWASP Top 10 시각 으로 점검해 줘" 형태의 user 발화 시.

Skip 조건:

  • axis-set 이 web-sec 미포함 (AI/LLM only / Crypto only / Social-eng only 등 단일 lane 시).
  • 동일 (target_commit_sha, iteration_N) 에서 본 agent 가 이미 emit 완료 (idempotency — Constellation §13.13.2 at-least-once 정합).
  • Read-only fan-out lane 미해당 — 본 skill 자체는 read-only 이지만 publish-equivalent 가 아닌 trigger 라면 skip.

Read the full file on GitHub · 418 lines

Changes

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.

  1. 12d ago First seen · 418 lines · 169 tokens per session scan A b94660bbfd75

Subscribe to this mod's changes

ultrasafe-web-api-attacker is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 169 tokens to every session and 7,178 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

search-threads

Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.

mostlyharmless-ai/watercooler · 35 tokens

ppgp

Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.

Fatboy-coder/ppgp · 53 tokens

watercooler-health

Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.

mostlyharmless-ai/watercooler · 49 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens