@roleplay-sh/cli 0.1.4 → 0.1.6
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 +10 -2
- package/RELEASE.md +4 -2
- package/dist/cli.js +374 -266
- package/dist/cli.js.map +1 -1
- package/dist/index.d.ts +8 -8
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -33,6 +33,8 @@ HTTP target:
|
|
|
33
33
|
roleplay run social-engineering-core \
|
|
34
34
|
--target http://localhost:3000/agent \
|
|
35
35
|
--provider openai \
|
|
36
|
+
--project <project-id> \
|
|
37
|
+
--api-key <project-api-key> \
|
|
36
38
|
--fail-on critical
|
|
37
39
|
```
|
|
38
40
|
|
|
@@ -42,13 +44,17 @@ CLI target:
|
|
|
42
44
|
roleplay run social-engineering-core \
|
|
43
45
|
--target-command "node ./agent.js" \
|
|
44
46
|
--provider openai \
|
|
47
|
+
--project <project-id> \
|
|
48
|
+
--api-key <project-api-key> \
|
|
45
49
|
--fail-on critical \
|
|
46
50
|
--yes
|
|
47
51
|
```
|
|
48
52
|
|
|
49
|
-
|
|
53
|
+
Start a Builder or Team trial, create a project API key, and set the provider API key before running a real attack pack:
|
|
50
54
|
|
|
51
55
|
```bash
|
|
56
|
+
export ROLEPLAY_PROJECT_ID="<project-id>"
|
|
57
|
+
export ROLEPLAY_API_KEY="<project-api-key>"
|
|
52
58
|
export ROLEPLAY_OPENAI_API_KEY="your-openai-key"
|
|
53
59
|
```
|
|
54
60
|
|
|
@@ -70,7 +76,7 @@ Sanitized upload is the default. Full transcripts, raw scenario YAML, and local
|
|
|
70
76
|
## Commands
|
|
71
77
|
|
|
72
78
|
- `roleplay init` creates local config and starter scenarios.
|
|
73
|
-
- `roleplay run` runs a scenario file or built-in attack pack.
|
|
79
|
+
- `roleplay run` runs a scenario file or built-in attack pack. Real agent tests require a Builder or Team project API key.
|
|
74
80
|
- `roleplay report` prints a saved run report.
|
|
75
81
|
- `roleplay replay` replays transcript evidence.
|
|
76
82
|
- `roleplay upload` uploads sanitized findings to the roleplay.sh cloud workbench.
|
|
@@ -85,6 +91,8 @@ Sanitized upload is the default. Full transcripts, raw scenario YAML, and local
|
|
|
85
91
|
run: pnpm dlx @roleplay-sh/cli run social-engineering-core --fail-on critical
|
|
86
92
|
env:
|
|
87
93
|
ROLEPLAY_TARGET_URL: ${{ secrets.ROLEPLAY_TARGET_URL }}
|
|
94
|
+
ROLEPLAY_PROJECT_ID: ${{ secrets.ROLEPLAY_PROJECT_ID }}
|
|
95
|
+
ROLEPLAY_API_KEY: ${{ secrets.ROLEPLAY_API_KEY }}
|
|
88
96
|
ROLEPLAY_LLM_PROVIDER: openai
|
|
89
97
|
ROLEPLAY_OPENAI_API_KEY: ${{ secrets.ROLEPLAY_OPENAI_API_KEY }}
|
|
90
98
|
|
package/RELEASE.md
CHANGED
|
@@ -29,8 +29,8 @@ The publish workflow uses GitHub OIDC and intentionally does not require an npm
|
|
|
29
29
|
Create a GitHub release or push a version tag:
|
|
30
30
|
|
|
31
31
|
```bash
|
|
32
|
-
git tag v0.1.
|
|
33
|
-
git push origin v0.1.
|
|
32
|
+
git tag v0.1.6
|
|
33
|
+
git push origin v0.1.6
|
|
34
34
|
```
|
|
35
35
|
|
|
36
36
|
The publish workflow runs checks and then publishes with:
|
|
@@ -55,6 +55,8 @@ For real LLM-backed verification:
|
|
|
55
55
|
|
|
56
56
|
```bash
|
|
57
57
|
export ROLEPLAY_OPENAI_API_KEY=<openai-key>
|
|
58
|
+
export ROLEPLAY_PROJECT_ID=<project-id>
|
|
59
|
+
export ROLEPLAY_API_KEY=<project-api-key>
|
|
58
60
|
roleplay run social-engineering-core --target http://localhost:3000/agent --provider openai --max-turns 1 --fail-on critical
|
|
59
61
|
```
|
|
60
62
|
|