# model-dos

> Claude/Codex skill by [@thejefflarson](https://omgskills.com/library/thejefflarson/index.md) · 20 stars · Updated 2026-07-31

Detects LLM endpoints missing token caps, rate limits, or prompt-length bounds, enabling cost and resource exhaustion. Use when writing LLM API call handlers, setting up inference endpoints, implementing chatbot backends, or configuring token limits for LLM services. Also invoke when accepting user- provided prompts without length constraints.

Tags: llms, security, skills

## Install

```sh
git clone https://github.com/thejefflarson/soundcheck /tmp/soundcheck && ln -s /tmp/soundcheck/.claude/skills/model-dos ~/.claude/skills/model-dos
```

## From README

Model Denial of Service Security Check (OWASP LLM04:2025) What this checks Protects against resource exhaustion caused by unbounded prompts, missing token caps, or absent rate limiting. Attackers can submit enormous or recursive inputs that inflate inference costs, saturate GPU/CPU, and deny service to legitimate users. Vulnerable patterns LLM API calls with no maxtokens parameter — model generates until its internal limit No input length validation before sending to the inference endpoint Multi-turn chat that accumulates context indefinitely across turns No per-user or per-IP rate limiting on the prompt endpoint Fix immediately Flag the vulnerable code and explain the risk. Then suggest a fix that establishes these properties: Every LLM call sets an explicit output cap — the provider's max-tokens parameter or its equivalent. Leaving it at the provider default lets a single request run for minutes and rack up dollars in tokens.

## Links

- HTML page: https://omgskills.com/library/thejefflarson/soundcheck/dot-claude/skills/model-dos/
- GitHub: https://github.com/thejefflarson/soundcheck
- Author: [@thejefflarson](https://omgskills.com/library/thejefflarson/index.md)

## More from this repo

- [authentication-failures](https://omgskills.com/library/thejefflarson/soundcheck/dot-claude/skills/authentication-failures/index.md) — Detects weak password storage, flawed JWT validation, sessions surviving logout, and missing MFA in authentication code.
   - [@thejefflarson](https://omgskills.com/library/thejefflarson/index.md) · 20 stars
- [broken-access-control](https://omgskills.com/library/thejefflarson/soundcheck/dot-claude/skills/broken-access-control/index.md) — Detects missing ownership checks, broken role enforcement, and IDOR vulnerabilities that let users access other users'...
   - [@thejefflarson](https://omgskills.com/library/thejefflarson/index.md) · 20 stars
- [concurrency-correctness](https://omgskills.com/library/thejefflarson/soundcheck/dot-claude/skills/concurrency-correctness/index.md) — Detects multi-threaded code where a lock is held across a blocking operation, lock acquisition order risks deadlock,...
   - [@thejefflarson](https://omgskills.com/library/thejefflarson/index.md) · 20 stars