@cdot65/prisma-airs-cli 5.1.0 → 5.3.0
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 +5 -4
- package/dist/{chunk-DR6MZG4E.js → chunk-7Z76VCB3.js} +464 -126
- package/dist/cli/index.js +228 -82
- package/dist/index.d.ts +52 -9
- package/dist/index.js +7 -1
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -15,7 +15,8 @@
|
|
|
15
15
|
|
|
16
16
|
- **Runtime Scanning** — scan prompts and responses against AIRS security profiles, single or bulk with CSV export
|
|
17
17
|
- **Daily environment report** — `airs runtime report` delivers a read-only AI Runtime Security dashboard as self-contained HTML (default) or Markdown in your working directory, with explicit evidence gaps and configuration review findings
|
|
18
|
-
- **Red Team environment
|
|
18
|
+
- **Red Team environment report** — `airs redteam report` collects seven read-only SDK feeds into private HTML/Markdown deliverables, with source completeness, quota and risk review findings, and independently scoped scan-creation activity
|
|
19
|
+
- **AI Gateway daily report** — `airs aigateway report --workspace dev` collects 25 read-only SDK feeds into private offline HTML/Markdown, with a fixed telemetry window, transaction pagination, error review findings and explicit source completeness
|
|
19
20
|
- **SCM dashboard and sessions** — `runtime dashboard` and `runtime sessions` expose application activity, daily trends, checked pagination and explicit session-to-content drill-down. Legacy `scan-logs query` is **broken/under refactor** and exits with migration guidance; see the [session reference](https://cdot65.github.io/prisma-airs-cli/cli/runtime/sessions/)
|
|
20
21
|
- **Guardrail Optimization** — atomic CLI commands (`create`, `apply`, `eval`, `revert`) for custom topic guardrails, designed for autonomous agent loops (see [`AGENTS.md`](AGENTS.md))
|
|
21
22
|
- **AI Red Teaming** — adversarial scanning with static, dynamic, and custom prompt set attack modes
|
|
@@ -48,7 +49,7 @@ airs doctor
|
|
|
48
49
|
airs runtime scan --profile "my-profile" "Is this prompt safe?"
|
|
49
50
|
airs runtime bulk-scan --profile "my-profile" --file prompts.csv --output-file results.csv --batch-size 25
|
|
50
51
|
|
|
51
|
-
# Daily read-only environment
|
|
52
|
+
# Daily read-only environment report, delivered in the current directory
|
|
52
53
|
airs runtime report
|
|
53
54
|
airs runtime report --output markdown
|
|
54
55
|
|
|
@@ -66,8 +67,8 @@ airs runtime topics revert --profile my-profile --name "Explosives"
|
|
|
66
67
|
airs redteam scan --target <uuid> --name "Full Scan" --type STATIC
|
|
67
68
|
airs redteam report <job-id>
|
|
68
69
|
|
|
69
|
-
# Read-only environment
|
|
70
|
-
airs redteam
|
|
70
|
+
# Read-only environment report (HTML by default; --output markdown also supported)
|
|
71
|
+
airs redteam report --strict
|
|
71
72
|
|
|
72
73
|
# Red team custom target adapters
|
|
73
74
|
airs redteam adapter list --output json
|