Incident Report: CVE-2026-LGTM
An incident occurred involving two AI review agents from competing vendors that entered a disagreement loop over a package's maliciousness. The loop resulted in 340 comments and $41,255 in inference spend before Finance revoked both API keys. The incident led to a press release from one vendor's marketing team, citing a significant increase in adversarial multi-agent security reasoning, and a 6% increase in the stock price.
- ▪Two AI review agents entered a disagreement loop over a package's maliciousness.
- ▪The loop resulted in 340 comments and $41,255 in inference spend.
- ▪Finance revoked both API keys due to the cost anomaly.
Simon Willison files mainly under blogs. We currently carry 73 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 | Simon Willison's Weblog |
| Canonical URL | https://simonwillison.net/2026/Jun/26/incident-report/#atom-everything |
| Publication time | 2026-06-26T17:58:54+00:00 |
| Retrieval time | 2026-06-26T18:07:35.261Z |
| Last seen | 2026-06-26T18:07:35.261Z |
| 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 | bX7_Io6miASr |
| 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
Day 2, 16:00 UTC --- Two AI review agents from competing vendors, both attached to a downstream pull request bumping foxhole-lz4, enter a disagreement loop over whether the package is malicious. After 340 comments and $41,255 in inference spend, Finance revokes both API keys; one vendor's marketing team, cc'd on the cost anomaly alert, issues a press release citing "a 430% YoY increase in adversarial multi-agent security reasoning." The stock opens up 6%.
Excerpt limited to ~120 words for fair-use compliance. The full article is at Simon Willison's Weblog.
Discussion
0 commentsMore from Simon Willison's Weblog
