@sandrobuilds/tracerney 0.9.19 → 0.9.20
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 +27 -7
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
Lightweight prompt injection detection for LLM applications. Runs 100% locally with zero data leaving your server.
|
|
4
4
|
|
|
5
|
+
> 🚀 **Explore the full platform at [tracerney.com](https://www.tracerney.com)** — includes dashboard, analytics, API management, and team collaboration tools.
|
|
6
|
+
|
|
5
7
|
## Install
|
|
6
8
|
|
|
7
9
|
```bash
|
|
@@ -72,16 +74,34 @@ if (result.suspicious) {
|
|
|
72
74
|
- Detects: instruction overrides, role-play jailbreaks, context confusion, code execution risks, data extraction attempts, and more
|
|
73
75
|
|
|
74
76
|
**Layer 2:** LLM Sentinel (Pro - $9/month)
|
|
75
|
-
- AI-powered response verification
|
|
76
|
-
-
|
|
77
|
-
-
|
|
78
|
-
-
|
|
79
|
-
-
|
|
77
|
+
- **AI-powered response verification** — LLM-based analysis for novel attack patterns
|
|
78
|
+
- **Context-aware scanning** — understands your application's specific security policies
|
|
79
|
+
- **Delimiter salting** — prevents prompt injection through response boundaries
|
|
80
|
+
- **Zero prompt storage** — responses are analyzed in-memory, never saved or logged
|
|
81
|
+
- **Structured threat metadata** — detailed fingerprints for audit trails and tracking
|
|
82
|
+
- **Advanced rate limiting** — prevents cost spikes with intelligent throttling
|
|
80
83
|
|
|
81
|
-
## Pricing
|
|
84
|
+
## Pricing & Usage
|
|
82
85
|
|
|
83
86
|
- **Free Tier:** 50 scans/month with Layer 1 pattern detection
|
|
84
|
-
- **Pro Tier:** 2,500 scans/month with Layer 1 + Layer 2 LLM verification
|
|
87
|
+
- **Pro Tier:** 2,500 scans/month with Layer 1 + Layer 2 LLM verification ($9/month)
|
|
88
|
+
|
|
89
|
+
---
|
|
90
|
+
|
|
91
|
+
## Ready for Advanced Protection?
|
|
92
|
+
|
|
93
|
+
Layer 2 (LLM Sentinel) adds AI-powered verification with **context-aware** threat detection and **zero prompt storage** — all responses are analyzed in-memory and immediately discarded.
|
|
94
|
+
|
|
95
|
+
**[Start Your Free Trial or Upgrade to Pro](https://www.tracerney.com/docs)** at tracerney.com
|
|
96
|
+
|
|
97
|
+
Includes:
|
|
98
|
+
- Dashboard with threat analytics
|
|
99
|
+
- API key management
|
|
100
|
+
- Team collaboration features
|
|
101
|
+
- Detailed threat fingerprints for compliance
|
|
102
|
+
- Priority support for Pro members
|
|
103
|
+
|
|
104
|
+
---
|
|
85
105
|
|
|
86
106
|
## License
|
|
87
107
|
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@sandrobuilds/tracerney",
|
|
3
|
-
"version": "0.9.
|
|
4
|
-
"description": "Lightweight prompt injection detection
|
|
3
|
+
"version": "0.9.20",
|
|
4
|
+
"description": "Lightweight prompt injection detection with Layer 1 (258 patterns) + Layer 2 (AI verification). Runs locally with zero data storage. Upgrade to Pro for context-aware threat analysis at tracerney.com",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
7
7
|
"types": "dist/index.d.ts",
|