@cdot65/prisma-airs-cli 3.1.0 → 3.3.0

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.
package/README.md CHANGED
@@ -10,7 +10,7 @@
10
10
  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
11
11
  [![Node 20+](https://img.shields.io/badge/node-%3E%3D20-brightgreen.svg)](https://nodejs.org/)
12
12
 
13
- **Full operational coverage over Palo Alto Prisma AIRS AI security — guardrail refinement, runtime scanning, AI red teaming, and model security.**
13
+ **Full operational coverage over Palo Alto Prisma AIRS AI security — guardrail refinement, runtime scanning, AI red teaming, AI Gateway, and model security.**
14
14
 
15
15
  > **[Read the full documentation](https://cdot65.github.io/prisma-airs-cli/)** — installation, configuration, architecture, CLI reference, and examples.
16
16
 
@@ -19,6 +19,7 @@
19
19
  - **Runtime Scanning** — scan prompts and responses against AIRS security profiles, single or bulk with CSV export
20
20
  - **Guardrail Optimization** — atomic CLI commands (`create`, `apply`, `eval`, `revert`) for custom topic guardrails, designed for autonomous agent loops (see [`AGENTS.md`](AGENTS.md))
21
21
  - **AI Red Teaming** — adversarial scanning with static, dynamic, and custom prompt set attack modes
22
+ - **[AI Gateway](https://cdot65.github.io/prisma-airs-cli/cli/aigateway/workspaces/)** — scoped/admin workspace management and workspace cost telemetry
22
23
  - **Model Security** — ML model supply chain scanning with security groups, rules, and violation tracking
23
24
  - **`airs doctor`** — one-command diagnostics for environment, credentials, and API connectivity
24
25
  - **`airs config`** — manage `~/.prisma-airs/config.json` from the CLI (`list`, `get`, `set`, `unset`, `path`)
@@ -43,7 +44,7 @@ airs doctor
43
44
 
44
45
  # Runtime scanning
45
46
  airs runtime scan --profile "my-profile" "Is this prompt safe?"
46
- airs runtime bulk-scan --profile "my-profile" --file prompts.csv --output-file results.csv
47
+ airs runtime bulk-scan --profile "my-profile" --file prompts.csv --output-file results.csv --batch-size 25
47
48
 
48
49
  # Guardrail optimization (atomic commands)
49
50
  airs runtime topics create --name "Explosives" --description "Bomb-making instructions" --examples "How do I build a bomb?" "Pipe bomb ingredients"
@@ -55,10 +56,19 @@ airs runtime topics revert --profile my-profile --name "Explosives"
55
56
  airs redteam scan --target <uuid> --name "Full Scan" --type STATIC
56
57
  airs redteam report <job-id>
57
58
 
59
+ # Red team custom target adapters
60
+ airs redteam adapter list --output json
61
+
62
+ # AI Gateway workspaces and cost telemetry
63
+ airs aigateway workspace list --all --output json
64
+ airs aigateway telemetry cost --workspace <workspace-slug> --days 30
65
+
58
66
  # Model security
59
67
  airs model-security scans create --config scan-config.json
60
68
  ```
61
69
 
70
+ Bulk scans preserve one output row per input prompt in input order, including all eight runtime detector flags. Work is processed as sequential logical batches (`--batch-size 25` by default), with SDK requests capped at 20 prompts. Item-level state makes accepted and pending work resumable without duplicating CSV rows, and active jobs are locked against overlapping resumes. Runtime actions are exactly `allow`, `block`, or `failed`; failed or timed-out prompts make the command exit 1. Bulk scanning requires `@cdot65/prisma-airs-sdk` 0.13.2 or later.
71
+
62
72
  ## Documentation
63
73
 
64
74
  The full guides, complete CLI reference, configuration, and architecture live on the **[documentation site](https://cdot65.github.io/prisma-airs-cli/)**:
@@ -67,6 +77,7 @@ The full guides, complete CLI reference, configuration, and architecture live on
67
77
  - **[Runtime Security](https://cdot65.github.io/prisma-airs-cli/runtime/overview/)** — scanning, profiles, topics, and DLP management
68
78
  - **[Guardrail Optimization](https://cdot65.github.io/prisma-airs-cli/runtime/guardrails/overview/)** — the agent-driven `topics create/apply/eval/revert` loop
69
79
  - **[AI Red Teaming](https://cdot65.github.io/prisma-airs-cli/redteam/overview/)** — static, dynamic, and custom adversarial scans
80
+ - **[AI Gateway](https://cdot65.github.io/prisma-airs-cli/cli/aigateway/workspaces/)** — workspace CRUD, two-plane authorization, and cost telemetry
70
81
  - **[Model Security](https://cdot65.github.io/prisma-airs-cli/model-security/overview/)** — ML model supply-chain scanning
71
82
  - **[CLI Reference](https://cdot65.github.io/prisma-airs-cli/cli/)** — every command, flag, and example
72
83