Cisco Foundry Security Spec: Open specification for agentic security evaluation
Cisco has introduced an open specification for agentic AI security evaluation called Foundry. This specification is based on extensive internal experience and aims to provide a flexible architecture for organizations to build their own implementations. It emphasizes the importance of design decisions and offers a framework for continuous improvement in security evaluations.
- ▪Foundry Security Spec is an open specification developed by Cisco's Advanced Security Initiatives Group.
- ▪The specification includes core agent roles, governance requirements, and functional requirements with rationale.
- ▪Foundry is designed to be infrastructure-neutral, allowing organizations to implement their own systems based on the provided blueprint.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 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/CiscoDevNet/foundry-security-spec |
| Publication time | Sat, 23 May 2026 19:30:18 +0000 |
| Retrieval time | 2026-05-23T19:37:27.624Z |
| Last seen | 2026-05-23T19:37:27.624Z |
| 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 | RKNMM-ir7fmM |
| 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
Foundry Security Spec An open specification for agentic AI security evaluation, from Cisco. Cisco's Advanced Security Initiatives Group has built and operated an agentic security evaluation internally across several iterations and deployment models, and along the way accumulated a long list of design decisions that turned out to matter and a longer list that turned out not to. Foundry distills that experience into a single, organization-neutral specification. It is the design that, across those iterations, consistently proved most effective. It is not our code. It is the shape of a system that works, with every lesson we learned written down as a requirement and every place where the right answer depends on your infrastructure left as an explicit open question.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.