@cdot65/prisma-airs-cli 1.0.0 → 1.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +42 -4
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,6 +1,7 @@
1
1
  # Prisma AIRS CLI
2
2
 
3
3
  [![CI](https://github.com/cdot65/prisma-airs-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/cdot65/prisma-airs-cli/actions/workflows/ci.yml)
4
+ [![npm](https://img.shields.io/npm/v/@cdot65/prisma-airs-cli)](https://www.npmjs.com/package/@cdot65/prisma-airs-cli)
4
5
  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
5
6
  [![Node 20+](https://img.shields.io/badge/node-%3E%3D20-brightgreen.svg)](https://nodejs.org/)
6
7
 
@@ -8,19 +9,42 @@
8
9
 
9
10
  > **[Read the full documentation](https://cdot65.github.io/prisma-airs-cli/)** — installation, configuration, architecture, CLI reference, and examples.
10
11
 
12
+ ## Features
13
+
14
+ - **Runtime Scanning** — scan prompts and responses against AIRS security profiles, single or bulk with CSV export
15
+ - **Guardrail Generation** — LLM-driven iterative refinement loop that generates, deploys, tests, and improves custom topic definitions until a coverage target is met
16
+ - **AI Red Teaming** — adversarial scanning with static, dynamic, and custom prompt set attack modes
17
+ - **Model Security** — ML model supply chain scanning with security groups, rules, and violation tracking
18
+ - **Profile Audits** — multi-topic evaluation with per-topic metrics and cross-topic conflict detection
19
+ - **Cross-run Memory** — persists learnings across guardrail generation runs for faster convergence
20
+
11
21
  ## Install
12
22
 
13
23
  ```bash
14
24
  npm install -g @cdot65/prisma-airs-cli
15
25
  ```
16
26
 
17
- Requires **Node.js >= 20**.
27
+ Requires **Node.js >= 20**. Also available as a [Docker image](https://github.com/cdot65/prisma-airs-cli/pkgs/container/prisma-airs-cli).
18
28
 
19
29
  ## Quick Start
20
30
 
21
31
  ```bash
32
+ # Configure credentials
22
33
  cp .env.example .env # add your API keys
23
- airs runtime topics generate # interactive guardrail generation
34
+
35
+ # Runtime scanning
36
+ airs runtime scan --profile "my-profile" "Is this prompt safe?"
37
+ airs runtime bulk-scan --profile "my-profile" --input prompts.csv --output results.csv
38
+
39
+ # Guardrail generation (interactive)
40
+ airs runtime topics generate
41
+
42
+ # Red team scanning
43
+ airs redteam scan --target "my-target" --type STATIC
44
+ airs redteam report <job-id>
45
+
46
+ # Model security
47
+ airs model-security scans create --group <group-id>
24
48
  ```
25
49
 
26
50
  ## Commands
@@ -33,9 +57,23 @@ airs runtime topics generate # interactive guardrail generation
33
57
  | `runtime profiles` | Security profile CRUD + multi-topic `audit` |
34
58
  | `runtime api-keys` | API key management |
35
59
  | `runtime customer-apps` | Customer app CRUD |
60
+ | `runtime deployment-profiles` | Deployment profile listing |
61
+ | `runtime dlp-profiles` | DLP profile listing |
36
62
  | `runtime scan-logs` | Scan log querying |
37
- | `redteam` | Adversarial scanning — targets, prompt sets, scans, reports |
38
- | `model-security` | ML model supply chain security — groups, rules, scans, labels |
63
+ | `redteam scan` | Adversarial scanning (STATIC, DYNAMIC, CUSTOM) |
64
+ | `redteam targets` | Red team target CRUD |
65
+ | `redteam prompt-sets` | Custom prompt set management |
66
+ | `model-security groups` | Security group CRUD |
67
+ | `model-security rules` | Security rule management |
68
+ | `model-security scans` | Model security scanning |
69
+
70
+ ## Configuration
71
+
72
+ Credentials are configured via environment variables or `~/.prisma-airs/config.json`. See [`.env.example`](.env.example) for the full list.
73
+
74
+ **Required for scanning:** `PANW_AI_SEC_API_KEY`
75
+ **Required for management:** `PANW_MGMT_CLIENT_ID`, `PANW_MGMT_CLIENT_SECRET`, `PANW_MGMT_TSG_ID`
76
+ **Required for guardrail generation:** one LLM provider key + scanning + management credentials
39
77
 
40
78
  ## License
41
79
 
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@cdot65/prisma-airs-cli",
3
3
  "packageManager": "pnpm@10.6.5",
4
- "version": "1.0.0",
4
+ "version": "1.0.1",
5
5
  "description": "CLI and library for Palo Alto Prisma AIRS — guardrail refinement, AI red teaming, model security scanning, profile audits",
6
6
  "type": "module",
7
7
  "main": "dist/index.js",