Generative AI
ImplementedGenAI (static)
The LLM / RAG / agent surface in a repository, without running it: excessive agency, identity, and prompt-injection surface in the code.
Family facts
- Code
- FAM-GENAI-STATIC
- Status
- ready — code maturity
- Availability
- available — whether it is offerable
- Ingest
- pull — how a target enters
- Rules of Engagement
- Not required
- Kind
- Family (a selectable assessment)
What it decides
Whether the code wires an AI system in a way that structurally enables excessive agency or an injection path to a privileged action.
How it works
It models the AI application’s structure and treats model and retrieval output as untrusted, expressing risk as invariants over a dataflow — for example “untrusted input must not reach the prompt” or “retrieved content must not reach a privileged tool”.
A deterministic verifier settles each invariant; where a store’s write-ACL or a tool’s authority cannot be resolved statically, the verdict is UNKNOWN, not “clean”.
Declared limits
The architecture graph covers Python plus a first-pass JS/TS front end; other languages degenerate to a single node. The deeper agentic/RAG classes (taint-to-tool, unscoped retrieval, unbounded loops) are not yet end-to-end verified.
References
References point to public, well-known technical sources for further study.
Related articles