AgentReadyHomeAgent ListingPricing

← Palo Alto Networks Prisma AIRS

Palo Alto Networks Prisma AIRS — agentic threat model

5.3AIVSS 5.3 · Medium

Prisma AIRS is a security-focused runtime protection platform and SDK rather than an autonomous agent, presenting low inherent agentic risk but holding high systemic risk as a critical security control point for enterprise AI workflows.

OWASP AIVSS score rationale

AIVSS = (CVSS_Base + AARS) × Mitigation_Factor, where AARS = (10 − CVSS_Base) × (Factor_Sum / 10) × ThM
CVSS base 8.5AARS uplift 0.32Factor sum 2.1/10Threat ×1.0Mitigation ×0.6
Autonomy of Action
0.10
Goal-Driven Planning
0.10
Self-Modification
0.00
Dynamic Tool Use
0.20
Persistent Memory
0.20
Contextual Awareness
0.60
Dynamic Identity
0.10
Multi-Agent Interactions
0.30
Non-Determinism
0.20
Opacity & Reflexivity
0.30

Scored with the canonical OWASP AIVSS formula (AIVSS calculator reference); agentic risk factors estimated from the agent’s described capabilities.

MAESTRO 7-layer threat model

Per-layer threats for this agent. Layers tagged “not certain from listing” are general, caveated commentary where the public description didn’t pin that layer.

L1 · Foundation Models⚠ not certain from listing

Not certain from the listing — The listing does not specify which foundation models Prisma AIRS itself uses (if any) to perform threat detection, though it secures other models against adversarial examples and prompt injection.

L2 · Data Operations⚠ not certain from listing

Not certain from the listing — While it prevents data leakage and memory poisoning, the listing does not detail Prisma AIRS's own training data, vector stores, or data operations.

L3 · Agent Frameworks✓ mapped

Prisma AIRS provides a Python SDK and integrates with the Model Context Protocol (MCP) Server to secure agent frameworks against tool misuse, memory poisoning, and insecure integrations.

L4 · Deployment & Infrastructure⚠ not certain from listing

Not certain from the listing — It is a SaaS-based platform with SDK integration, designed to run in production environments, but specific sandboxing or hosting infrastructure details of the SaaS itself are not detailed.

L5 · Evaluation & Observability✓ mapped

Acts as a runtime security and threat detection layer, integrating with enterprise SecOps platforms to monitor, log, and prevent prompt injection, malicious code, and data leakage.

L6 · Security & Compliance (cross-cutting)✓ mapped

It is a dedicated security platform designed to harden AI agents, detect malicious URLs, and prevent tool misuse, serving as a core security control for enterprise AI compliance.

L7 · Agent Ecosystem✓ mapped

Secures agentic workflows and multi-agent environments via the Prisma AIRS MCP Server, protecting against cascading failures and rogue agent behaviors in production.

MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).

These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.