AI Skill Security Rules

Table of Contents

Configure Identity and Access Management

AI Skill Security Rules

Learn about the built-in security rules that evaluate uploaded skills for security and governance risks, and how enabling and blocking settings control scan verdicts.

Where Can I Use This?	What Do I Need?
Prisma AIRS (AI Skill Security)	No License required for preview

Each uploaded skill is evaluated against a set of built-in security rules designed to identify behaviors that may introduce security or operational risk. A single Default Security Group contains all built-in security and governance rules evaluated during every scan.

Rule	Description
Prompt Integrity Check	Detects embedded instructions intended to manipulate or override expected agent behavior.
Arbitrary Code Execution Check	Detects executable code or patterns capable of performing actions beyond the skill's documented purpose.
Secrets Disclosure Check	Detects unauthorized access to credentials, API keys, tokens, and other sensitive information.
Data Exfiltration Check	Detects outbound communication or data transfers that may expose sensitive information.
Obfuscated Behavior Check	Detects actions performed without appropriate visibility, logging, or user awareness.
Behavior Integrity Check	Detects modifications to agent configuration, instructions, or persistent state.
Excessive Permissions Check	Detects autonomous behaviors or capabilities that exceed expected operational boundaries.

Each rule is controlled by two toggles:

Enabled — When this toggle is off, the rule is not evaluated.
Blocking — When this toggle is on, a finding from the rule's detectors produces a Blocked verdict. When it is off, the finding is still recorded but does not affect the verdict (alert only). The Blocking toggle is unavailable while Enabled is off.

Enabled	Blocking	Behavior
On	On	Block — a finding fails the scan verdict.
On	Off	Alert only — finding recorded, not counted towards scan outcome.
Off	NA	Disabled — not evaluated.

Configuration changes apply only to subsequent scans. In-flight and completed scans are not affected. To modify rule settings, see Configure AI Skill Security Rules.

Configure Identity and Access Management

Configure AI Skill Security Rules

Prisma AIRS Docs

AI Skill Security Rules

Prisma AIRS Docs

AI Skill Security Rules

Activation & Onboarding

Next-Generation Firewalls

Cloud-Delivered Security Services

Network Security

Visibility & Monitoring