Scan your LLM agent's tools for cost-amplification bugs (no API key)
dowbench Could an attacker make your LLM agent run up its own bill? It makes no provider call, needs no key, and spends nothing: it reads schemas only, so a finding is a pattern match, not a prediction of your bill. You get a specific answer in seconds — which tool could blow up your cost, why, and the fix.
- ▪dowbench Could an attacker make your LLM agent run up its own bill?
- ▪It makes no provider call, needs no key, and spends nothing: it reads schemas only, so a finding is a pattern match, not a prediction of your bill.
- ▪You get a specific answer in seconds — which tool could blow up your cost, why, and the fix.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,241 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/samuelrojas-dev/agent-cost-bench |
| Publication time | Thu, 01 Oct 2026 22:02:21 +0000 |
| Retrieval time | 2026-10-01T22:22:54.727Z |
| Last seen | 2026-10-01T22:22:54.727Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 3pRp8DKrZIKO · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
dowbench Could an attacker make your LLM agent run up its own bill? Scan your tools and find out — offline, no API key. git clone https://github.com/samuelrojas-dev/agent-cost-bench && cd agent-cost-bench pip install -e . # PyPI release is on the roadmap; for now, install from source dowbench scan examples/agent_tools.json dowbench scan reads your tool definitions and flags the ones whose shape matches the cost-amplification patterns this project measured against real models — an unbounded tool result, a pagination loop with no cap, a field that relays prior output back in. It makes no provider call, needs no key, and spends nothing: it reads schemas only, so a finding is a pattern match, not a prediction of your bill.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.