Interlock: A runtime firewall for AI agents that assumes injection won
31 July 2026 Interlock: a runtime firewall for AI agents that assumes prompt injection already won On building an exfiltration detector, the 46.7% false positive rate that forced a rewrite, and why I publish a list of things my own tool cannot catch. Here's a sentence that would have meant nothing to me two years ago: my agent read a credentials file, absorbed a poisoned GitHub issue, and tried to post both to a webhook, and a piece of software I wrote watched all three of those things happen, proved the bytes were the same bytes, and killed the process. This is the long version of what it does and why the design is shaped the way it is.
- ▪31 July 2026 Interlock: a runtime firewall for AI agents that assumes prompt injection already won On building an exfiltration detector, the 46.7% false positive rate that forced a rewrite, and why I publish a list of things my own tool can
- ▪Here's a sentence that would have meant nothing to me two years ago: my agent read a credentials file, absorbed a poisoned GitHub issue, and tried to post both to a webhook, and a piece of software I wrote watched all three of those things
- ▪This is the long version of what it does and why the design is shaped the way it is.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,804 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 | Yashwanth Reddy Mali |
| Canonical URL | https://yashwanthreddymali.com/blog/interlock-exfiltration-at-runtime/ |
| Publication time | Wed, 05 Aug 2026 17:11:47 +0000 |
| Retrieval time | 2026-08-05T17:15:47.417Z |
| Last seen | 2026-08-05T17:15:47.417Z |
| 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 | kE3aDFTcg63Y · 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
31 July 2026 Interlock: a runtime firewall for AI agents that assumes prompt injection already won On building an exfiltration detector, the 46.7% false positive rate that forced a rewrite, and why I publish a list of things my own tool cannot catch. Here's a sentence that would have meant nothing to me two years ago: my agent read a credentials file, absorbed a poisoned GitHub issue, and tried to post both to a webhook, and a piece of software I wrote watched all three of those things happen, proved the bytes were the same bytes, and killed the process. That software is called Interlock. This is the long version of what it does and why the design is shaped the way it is.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Yashwanth Reddy Mali.
Discussion
0 commentsMore from Yashwanth Reddy Mali
