Embed in a route
<FigureFromSource sourcePath="content/publications/figures/products/code-scanner.dsl.md" figureId="SCN-01" />
SCN-01
AI-Native Scanner Coverage
The scanner evaluates AI-specific code and workflow surfaces that conventional AppSec categories do not fully describe.
coverage matrix
| Discovery | Analysis | Evidence | Retest | |
|---|---|---|---|---|
| Prompts and instructionsSystem prompts, templates, policy text, and instruction boundaries. | Covered | Covered | Covered | Covered |
| Retrieval and contextCorpus access, provenance, tenant boundaries, and prompt assembly. | Covered | Covered | Covered | Partial |
| Agents and orchestrationPlanning, delegation, memory, and workflow transitions. | Covered | Partial | Partial | Planned |
| Tools and MCPTool schemas, invocation boundaries, and consequence-bearing actions. | Covered | Covered | Covered | Partial |
| Identity and authorityUser, agent, service, and delegated permissions. | Covered | Partial | Partial | Planned |
| Evidence and lifecycleFinding state, provenance, remediation, and rescan behavior. | Not applicable | Covered | Covered | Covered |
CoveredPartialPlannedNot applicable
About this figure
AI-native applications introduce security surfaces that are not fully captured by conventional AppSec categories. This scanner focuses on the parts of the system where model behavior, orchestration, and authority intersect: prompts and instructions, retrieval and context, agents and workflows, tools and MCP integrations, identity and authorization, and evidence across the analysis lifecycle. The coverage model tracks work across discovery, analysis, evidence collection, and retest, distinguishing what is fully covered, partially covered, planned, unknown, or not applicable. By mapping these AI-specific surfaces to concrete analysis stages, the scanner provides a more accurate view of risk and assurance for systems built around LLMs, agents, and tool-using workflows.
Citation
AI-Native Scanner Coverage (SCN-01). AI Security LLC Figure Library. https://aisecurity.llc/publication-dsl/figures/SCN-01