agent-security-scanner-mcp 3.12.0 → 3.14.0
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 +55 -1
- package/package.json +1 -1
- package/packages/npm-bloom.json +0 -1
- package/packages/pypi-bloom.json +0 -1
- package/packages/rubygems-bloom.json +0 -1
package/README.md
CHANGED
|
@@ -1,6 +1,12 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
<img src="./prooflayer-scanner/logo.svg" alt="ProofLayer Logo" width="400"/>
|
|
4
|
+
|
|
1
5
|
# agent-security-scanner-mcp
|
|
2
6
|
|
|
3
|
-
Security scanner for AI coding agents and autonomous assistants
|
|
7
|
+
**Security scanner for AI coding agents and autonomous assistants**
|
|
8
|
+
|
|
9
|
+
Scans code for vulnerabilities, detects hallucinated packages, and blocks prompt injection — via MCP (Claude Code, Cursor, Windsurf, Cline) or CLI (OpenClaw, CI/CD).
|
|
4
10
|
|
|
5
11
|
[](https://www.npmjs.com/package/agent-security-scanner-mcp)
|
|
6
12
|
[](https://www.npmjs.com/package/agent-security-scanner-mcp)
|
|
@@ -8,6 +14,54 @@ Security scanner for AI coding agents and autonomous assistants. Scans code for
|
|
|
8
14
|
[](benchmarks/RESULTS.md)
|
|
9
15
|
[](https://github.com/sinewaveai/agent-security-scanner-mcp/actions/workflows/test.yml)
|
|
10
16
|
|
|
17
|
+
</div>
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## 🎯 Two Versions Available
|
|
22
|
+
|
|
23
|
+
### 🔥 ProofLayer (Lightweight) - **NEW!**
|
|
24
|
+
**Ultra-fast, zero-Python security scanner** — 81.5KB package, 4-second install
|
|
25
|
+
|
|
26
|
+
[](https://www.npmjs.com/package/@prooflayer/security-scanner)
|
|
27
|
+
[](https://www.npmjs.com/package/@prooflayer/security-scanner)
|
|
28
|
+
|
|
29
|
+
```bash
|
|
30
|
+
npm install -g @prooflayer/security-scanner
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
- ⚡ **4-second install** (vs 45s traditional scanners)
|
|
34
|
+
- 📦 **81.5KB package** (vs 50MB+ alternatives)
|
|
35
|
+
- 🚀 **Instant scans** - pure regex, no Python/LLM
|
|
36
|
+
- 🛡️ **400+ security rules** across 9 languages
|
|
37
|
+
- 🎯 **7 MCP tools** for AI agents
|
|
38
|
+
- ✅ **Zero dependencies** on Python
|
|
39
|
+
- 💯 **MIT licensed** - free for commercial use
|
|
40
|
+
|
|
41
|
+
[📖 ProofLayer Documentation →](./prooflayer-scanner/)
|
|
42
|
+
|
|
43
|
+
---
|
|
44
|
+
|
|
45
|
+
### 🔬 Full Version (Advanced)
|
|
46
|
+
**Enterprise-grade scanner** with AST analysis, taint tracking, and cross-file analysis
|
|
47
|
+
|
|
48
|
+
[](https://www.npmjs.com/package/agent-security-scanner-mcp)
|
|
49
|
+
|
|
50
|
+
```bash
|
|
51
|
+
npm install -g agent-security-scanner-mcp
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
- 🧬 **AST + Taint Analysis** - deep code understanding
|
|
55
|
+
- 🔍 **1,700+ security rules** across 12 languages
|
|
56
|
+
- 📊 **Cross-file tracking** - follow data flows
|
|
57
|
+
- 🎯 **11 MCP tools** + CLI commands
|
|
58
|
+
- 📦 **4.3M+ package verification** (bloom filters)
|
|
59
|
+
- 🐍 **Python analyzer** for advanced features
|
|
60
|
+
|
|
61
|
+
Continue reading below for full version documentation →
|
|
62
|
+
|
|
63
|
+
---
|
|
64
|
+
|
|
11
65
|
> **New in v3.11.0:** ClawHub ecosystem security scanning — scanned all 777 ClawHub skills and found 69.5% have security issues. New `scan-clawhub` CLI for batch scanning, 40+ prompt injection patterns, jailbreak detection (DAN mode, dev mode), data exfiltration checks. [See ClawHub Security Reports](./clawhub-security-reports/).
|
|
12
66
|
>
|
|
13
67
|
> **Also in v3.10.0:** ClawProof OpenClaw plugin — 6-layer deep skill scanner (`scan_skill`) with ClawHavoc malware signatures (27 rules, 121 patterns covering reverse shells, crypto miners, info stealers, C2 beacons, and OpenClaw-specific attacks), package supply chain verification, and rug pull detection.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "agent-security-scanner-mcp",
|
|
3
|
-
"version": "3.
|
|
3
|
+
"version": "3.14.0",
|
|
4
4
|
"mcpName": "io.github.sinewaveai/agent-security-scanner-mcp",
|
|
5
5
|
"description": "Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.",
|
|
6
6
|
"main": "index.js",
|