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 contactandrewchl-wq/turtle-mcp --skill security-owaspgit clone --depth 1 https://github.com/contactandrewchl-wq/turtle-mcpWrote 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/contactandrewchl-wq/turtle-mcp/security-owasp)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/security-owasp"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/security-owasp/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/contactandrewchl-wq/turtle-mcp/security-owasp"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/security-owasp.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 | $0.00078 | $0.01290 |
| Opus 5 | $0.00039 | $0.00645 |
| Sonnet 5 | $0.00016 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade B, and why
security-owasp scanned grade B with 2 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 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- No `curl | sh` sin pinning ni checksum (a menos que sea instalación interactiva con consentimiento). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- No `curl | sh` sin pinning ni checksum (a menos que sea instalación interactiva con consentimiento). How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security — OWASP Top 10 aplicado
Cuándo usar
- Diseñar o revisar un endpoint público.
- Auditoría de seguridad antes de release.
- Triage de un reporte de vulnerabilidad.
Complementa a [[secure-by-default]] (lista corta always-on); esta es la profunda.
A01 — Broken Access Control
Síntoma: un usuario accede o modifica algo que no debería.
- Por defecto denegar. Permisos explícitos, no implícitos.
- Autorización en el servidor, en cada handler. Cliente solo oculta UI.
- IDOR: nunca confíes en IDs del cliente. Verificá ownership en cada acceso a recurso (
WHERE id=? AND owner_id=?). - Sin métodos HTTP sin protección:
PUT/DELETE/POSTpor error rutean a un handler abierto.
Ver [[security-authn-authz]] para el detalle.
A02 — Cryptographic Failures
- HTTPS siempre. Sin "interno está bien sin TLS".
- Hash de contraseñas:
argon2id(preferido) obcrypt(12+). Nunca MD5, SHA1, SHA-256 pelado. - Cifrado: AES-GCM, ChaCha20-Poly1305. Sin ECB, sin CBC sin MAC.
- TLS ≥1.2, idealmente 1.3. Cipher suites modernas.
- Datos sensibles cifrados en reposo (BD, backups, logs).
- Tokens con suficiente entropía: 128+ bits, generados con CSPRNG (
crypto.randomBytes,secrets.token_bytes).
A03 — Injection
SQL, NoSQL, OS command, LDAP, ORM raw, template.
- Parametrización SIEMPRE. Sin
f"SELECT * FROM x WHERE id={id}". - Para queries dinámicas seguras: query builder con bindings o stored procs parametrizados.
- Shell: sin
exec(string); usá array de args (spawn(cmd, [args...])) o evitá del todo. - Template injection: no metas input de usuario en strings que después rendea un template engine sin escape.
- Validá whitelist (lo que sí), no blacklist (lo que no).
A04 — Insecure Design
- Modelá amenazas antes de codear lo crítico (STRIDE como base).
- Límites por defecto: rate limit, max size, max depth, timeout.
- Patrones de fallo seguro: si el authz falla → denegar, no permitir.
A05 — Security Misconfiguration
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.
- 12d ago First seen · 113 lines · 78 tokens per session scan B 913a72c23186
security-owasp is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 1,290 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
engram-memory
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
simplicio-loop
Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host…
simplicio-nest-gate
N-Nest protocol — multi-level gate-corrected agent tree. PRIME depth verification, BH port.port.port addressing, per-level confabulation catch.
simplicio-orient
Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their…
simplicio-autoresearch
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11…