Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after a top-up of $10 or more. Until Nov 30.

How it works
noorqureshi/ai-llm-dosAI, agents and MCP

ai-llm-dos

⁨Unbounded-consumption / denial-of-wallet attacks on LLM apps — force runaway tokens, cost, or latency. Load when testing an LLM product's limits/billing, on "LLM DoS", cost amplification, or resource exhaustion. Signals: user-controlled prompts/max_tokens, agent loops, no rate/'cost caps'.⁩

v2026.10.14-ee0e0c53 installs+3 in 7 days27 StarsMITsynced 22 hours ago

Install

No NotHoly CLI yet? Install it first.

$ curl -fsSL https://notholy.com/install.sh | sh
$ notholy skills install noorqureshi/ai-llm-dos

Writes to ⁦~/.notholy/skills⁩ after checking the signature and the SHA-256.

SignatureSigned, ed25519
NKCFzx6lk4…B5dcJ3Aw==The CLI checks the SHA-256 and the signature before it writes a file.
Package749e97c7…4a103801
749e97c7f22d…365f4a1038011 file · ⁦1.4 KB⁩
ScanLowno findings
The scan found nothing to flag in this version.See the full scan
Sourcegithub.com/NoorQureshi/security-skills/tree/main/skills/ai-ml/ai-llm-dos@ee0e0c5

When it applies

An LLM feature lets users drive expensive computation with weak limits. Unlike classic DoS, the damage is often financial (the provider bills per token) — "denial of wallet" — plus latency/availability.

Why it works

Inference cost scales with tokens and calls. If the app lets users control input size, output length (max_tokens), recursion (agent loops, tool chains), or call volume without hard caps, an attacker amplifies cost/latency far beyond normal use.

Method

  1. Input amplification: send very long inputs, or inputs that induce very long outputs ("repeat X 10000 times", "write an exhaustive…"); push max_tokens if client-controlled.
  2. Recursion / loops: with agents, craft prompts that trigger long tool-call loops or self-referential expansion (→ ai-agent-tool-abuse) that burn calls.
  3. Volume: bypass rate limits (→ web-rate-limit-bypass) and fan out concurrent expensive requests.
  4. Retrieval blow-up: in RAG, queries that pull huge context each call multiply token cost.
  5. Measure impact: latency spike, error/timeout rates, or (where visible) token/cost per request × achievable rate.

Gotchas

  • Frame it as impact (cost/availability), not just "it was slow" — quantify tokens/cost or a service degradation.
  • Respect RoE strictly — this can run up real bills / affect availability; prove with minimal, controlled requests, don't sustain an outage.
  • Defenders: cap input/output tokens, per-user quotas & spend caps, loop/tool budgets, timeouts.

Verify success

A single request (or a modest, controlled burst) demonstrably drives disproportionate token/cost or latency — showing missing consumption limits.

References

OWASP LLM Top 10 (2025) LLM10; "denial of wallet" research; provider rate/quota docs.

Files in this version

Permissions

PermissionDeclaredFound by the scan
Reads filesNoNo
Writes filesNoNo
Runs shell commandsNoNo
Uses the networkNoNo
Uses connectorsNoNo
Drives a browserNoNo

Scan findings

Reviewed on Nov 13, 2026

The scan found nothing to flag in this version.

A clean scan lowers the risk but does not prove a package is safe. Read what you install.

VersionPublishedCommitSHA-256SignaturePermission change
v2026.10.14-ee0e0c5Nov 13, 2026ee0e0c5749e97c7Signed–

Ask anything your scope allows.

Create an account, add credits and ask the first question in the chat or the terminal.

  1. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card. Pay per token, no subscription.

    $5.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login