LLM features
Model calls without a spend cap
Nothing limits how many tokens one user, or the whole app, can consume, so a loop or a hostile user runs up the provider bill.
TermsLLM feature (a product feature that calls a large language model, such as an assistant or a summariser) · golden set (a fixed list of model inputs with recorded expectations, re-run on every model or prompt change) · fault injection (making a dependency fail on purpose in staging to see what the user and the logs show)
criticalseverity if found in a releasesources verified 2026-09-21
Why AI-assisted code produces it
OWASP lists unbounded consumption (LLM10) in its 2025 Top 10 for LLM applications. Generated integrations call the provider and return; limits are infrastructure that has to be asked for.
The OWASP Top 10 for LLM Applications 2025 lists prompt injection (LLM01), sensitive information disclosure (LLM02), improper output handling (LLM05), excessive agency (LLM06), system prompt leakage (LLM07) and unbounded consumption (LLM10) among the ten risks.
Source: OWASP GenAI Security Project, 2025-03-12 · verified 2026-09-21
How we detect it
Exceed the per-user cap in a test account and the global cap in staging.
Most associated with
Tools: Cursor, GitHub Copilot, Claude Code, Windsurf, Lovable, Bolt
Checklist items that catch it
Spend cap enforced per user and globally
automated In a test account, make model calls past the per-user cap and, in staging, past the global daily cap.
Calls beyond either cap are refused with a user-visible message and a log entry; no further provider spend is recorded.
Dots: Starter, Growth, Scale. The item runs on every release for the plans marked.
Check your codebase for this pattern
The coverage audit lists which catalogue patterns apply to your critical flows. 5 business days, $1,200, credited to a first month.