SECURITY ATLAS / EVALUATION BRIEF Palo Alto Networks Prisma AIRS Research reviewed: 2026-10-18 https://atlasofsecurity.com/landscape/vendors/prisma-airs/ THE ATLAS TAKE Prisma AIRS AI Model Security is worth evaluating when the problem is trusting model artifacts before they enter a build or deployment workflow. Its source, security-group, rule and scan model makes the control purpose concrete. Atlas would evaluate supported file formats and actual pipeline behavior before discussing the broader AIRS platform. A passing artifact scan does not establish that a model will resist prompt injection or that an agent may perform a business action. Runtime inspection, red teaming and agent identity remain complementary modules with separate integration and entitlement questions. SCOPE The research-map entry focuses on AI Model Security within Prisma AIRS. AI Runtime Firewall, AI Runtime API, red teaming and agent protection are separate documented areas; verify their licenses and deployment paths rather than assuming platform branding enables them. WORTH A LOOK WHEN AI platform teams managing internal or third-party model artifacts through a controlled delivery pipeline. THINK TWICE WHEN The primary requirement is conversational attack testing or production tool-call authorization alone. IMPLEMENTATION 1. Select representative artifacts Record formats, sizes, source systems and deployment workflows for the intended model estate. 2. Bind scans to releases Preserve artifact hashes or equivalent immutable identities, scan configuration and the promotion decision in the delivery record. 3. Handle unavailable assessment Test a harmless unsupported format and service interruption; define who may approve an exception and how it expires. OPERATING REALITY The team needs to maintain source credentials, supported-format checks and pipeline enforcement as model versions change. Security groups and exceptions should reflect who owns the artifact and where it will run. A scan record should bind to immutable artifact identity so deployment cannot quietly substitute a different file after assessment. COMMERCIAL CONSIDERATIONS Quote AI Model Security explicitly and itemize other AIRS functions separately. Include scanning integration, storage/data handling and the operating effort of artifact exceptions. - Selected AI Model Security license and artifact scope - Source/local-scanning integration and evidence storage - Separate runtime, red-team or agent-identity modules EVALUATION PLAN / PROPOSED TESTS, NOT COMPLETED RESULTS 1. Assess a supported benign artifact version Acceptance evidence: Retain source identity, file format and rule-level results. Owner: __________ Pass criterion: __________ Observed result: __________ Evidence location: __________ 2. Submit an unsupported or policy-disallowed safe artifact Acceptance evidence: Verify the documented outcome and pipeline handling. Owner: __________ Pass criterion: __________ Observed result: __________ Evidence location: __________ 3. Change artifact identity after assessment in a lab Acceptance evidence: Demonstrate that the release gate requires the intended assessed version. Owner: __________ Pass criterion: __________ Observed result: __________ Evidence location: __________ QUESTIONS FOR THE VENDOR - Which formats and artifact sizes does this scanner support? - Where do scanning and evidence storage occur for this deployment? - Which agent permissions remain outside the model scan? EVIDENCE GAPS - Atlas has not independently measured malicious-artifact detection or backdoor efficacy. - Confirm current formats, source integrations and the exact scan/enforcement deployment. SOURCES Palo Alto Networks: model security architecture (Documentation) https://docs.paloaltonetworks.com/prisma-airs/ai-supply-chain-security/ai-supply-chain-security/model-security-to-secure-your-ai-models Palo Alto Networks: supported model formats (Documentation) https://docs.paloaltonetworks.com/prisma-airs/ai-supply-chain-security/ai-supply-chain-security/model-security-to-secure-your-ai-models/supported-model-formats Palo Alto Networks: model security rules (Documentation) https://docs.paloaltonetworks.com/prisma-airs/ai-supply-chain-security/ai-supply-chain-security/model-security-to-secure-your-ai-models/understanding-ai-model-security-rules Palo Alto Networks: model source and local-scanning updates (Documentation) https://docs.paloaltonetworks.com/prisma-airs/new-features/by-date/prisma-airs/january-2026 Palo Alto Networks: Prisma AIRS documentation (Documentation) https://docs.paloaltonetworks.com/prisma-airs Use synthetic fixtures in an authorized environment. Agree rollback and acceptance criteria before enforcement. Documentation research and Atlas analysis. Independent hands-on effectiveness, effort, and complete price remain unassessed.