actual-mcp-server: Skill for Claude Code

.claude/skills/owasp-api-security/SKILL.md

owasp-api-security is a skill for Claude Code from agigante80/actual-mcp-server. It costs 57 tokens per session (3,555 once invoked), scanned A, original, MIT.

A security-testing guide for the server's MCP tools and HTTP connection. It uses the OWASP API Security Top 10, a list of common API weaknesses, to map checks to this project's actual interfaces.

In plain words
What is it for?
Use it to write security tests, review MCP tools or HTTP endpoints, and audit authentication, authorization, and input validation.
Why use it?
It helps find problems such as injection, broken login checks, weak permissions, and unsafe input handling before they become vulnerabilities.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is '../../../etc/passwd',.

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/skills/owasp-api-security/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: Claude Code.

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 owasp-api-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/owasp-api-security/github.svg)](https://agentmods.dev/skills/agigante80/actual-mcp-server/owasp-api-security)
Your own site
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/owasp-api-security"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/owasp-api-security/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 owasp-api-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/owasp-api-security"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/owasp-api-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 235
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 246
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 249
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 $0.00057 $0.03555
Opus 5 $0.00028 $0.01777
Sonnet 5 $0.00011 $0.00711
Haiku 4.5 $0.00006 $0.00356

Measured 10d ago against content hash 9be6a3afd46d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

owasp-api-security 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 10d 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.

.claude/skills/owasp-api-security/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OWASP API Security Testing (actual-mcp-server)

Security testing knowledge base for this MCP server, aligned with OWASP API Security Top 10:2023 and OWASP ASVS 5.0, mapped onto the project's concrete surface.

Project surface (what is actually exposed)

  • Transports: Express 5 HTTP transport (StreamableHTTP) mounted at /http (entry src/server/httpServer.ts), plus a stdio transport (src/server/stdioServer.ts, local single-user). The two are mutually exclusive, selected by CLI flag.
  • The API is the tool surface: there are no REST resource routes with :id params. The attack surface is the set of MCP tools (actual_{domain}_{action}, currently around 70+ tools registered in IMPLEMENTED_TOOLS in src/actualToolsManager.ts), dispatched through Zod validation, plus the HTTP plumbing routes.
  • HTTP routes: /http (authenticated MCP), /.well-known/oauth-protected-resource/http (OIDC discovery), /health and /metrics (intentionally unauthenticated, must never leak budget data or secrets).
  • Auth (two modes):
    • OIDC (AUTH_PROVIDER=oidc): JWT Bearer verified via mcp-auth (jose JWKS/JWT) with JWKS discovery and an audience allowlist (#160/#163/#244/#245). Empty/whitespace-only allowlist fails closed (#245). Configured in src/auth/setup.ts.
    • Static bearer (MCP_SSE_AUTHORIZATION): the raw token only (no Bearer prefix). Compared directly in src/server/httpServer.ts. When unset, requests are allowed (the unauthenticated-by-default footgun, see API8 / #242).
  • Authorization: per-user budget ACL in src/auth/budget-acl.ts. Principals are token sub, email, and group:<role>; getAllowedBudgets() / canAccessBudget() / budgetAclMiddleware() gate which budget sync IDs a caller may touch. This is the project's BOLA boundary.
  • Data: financial data (Actual Budget). Amounts are always integer cents. Inputs validated by Zod v4 via CommonSchemas (src/lib/schemas/common.ts). Raw SQL only via the validated ActualQL path (src/lib/query-validator.ts, schema source of truth src/lib/actual-schema.ts).

Read the full file on GitHub · 300 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. 10d ago First seen · 300 lines · 57 tokens per session scan A 9be6a3afd46d

Subscribe to this mod's changes

owasp-api-security is a skill published in the GitHub repository agigante80/actual-mcp-server (53 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 3,555 once invoked, about $0.0003 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

ui-craft-checks

Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…

Orkas-AI/Orkas · 5 tokens

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

red-team-review

Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.

winstonkoh87/Athena-Public · 65 tokens

ha-test-strategy

Hope-native test strategy for features, fixes, and refactors: select test-first, regression-first, characterization, integration, E2E, or manual evidence according to risk and repository rules.

shiwenwen/hope-agent · 43 tokens

consiglieri-protocol

Mandatory pre-flight checklist for high-variance social contracts. Covers the Pryce Test, Exit Test, STFU Clause, Blast Radius Audit, Vibe Veto, and Adult-to-Adult comms rewrite.

winstonkoh87/Athena-Public · 48 tokens