hardstop 0.0.1
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 +34 -0
- package/index.js +15 -0
- package/package.json +29 -0
package/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
# 🛑 Hardstop
|
|
2
|
+
|
|
3
|
+
> The mechanical brake for AI-generated commands
|
|
4
|
+
|
|
5
|
+
**Status:** Placeholder - Full release coming soon
|
|
6
|
+
|
|
7
|
+
## What is Hardstop?
|
|
8
|
+
|
|
9
|
+
Hardstop is a pre-execution safety system for AI-generated shell commands. It acts as a fail-closed verification layer, blocking dangerous patterns (like `rm -rf ~/`, reverse shells, credential exfiltration) before they execute.
|
|
10
|
+
|
|
11
|
+
**Two-layer defense:**
|
|
12
|
+
- **Pattern matching** — Instant regex-based detection
|
|
13
|
+
- **LLM analysis** — Semantic analysis for edge cases
|
|
14
|
+
|
|
15
|
+
## Key Features
|
|
16
|
+
|
|
17
|
+
- **Fail-closed design** — If safety check fails, command is blocked (not allowed)
|
|
18
|
+
- **Cross-platform** — Unix + Windows patterns
|
|
19
|
+
- **Command chaining** — Analyzes all parts of piped/chained commands
|
|
20
|
+
- **Audit logging** — All decisions logged
|
|
21
|
+
|
|
22
|
+
## Coming Soon
|
|
23
|
+
|
|
24
|
+
- Full Claude Code plugin release
|
|
25
|
+
- MCP server integration
|
|
26
|
+
- Configurable security policies
|
|
27
|
+
|
|
28
|
+
## Links
|
|
29
|
+
|
|
30
|
+
- [GitHub Repository](https://github.com/frmoretto/hardstop)
|
|
31
|
+
|
|
32
|
+
## License
|
|
33
|
+
|
|
34
|
+
CC-BY-4.0
|
package/index.js
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Hardstop - The mechanical brake for AI-generated commands
|
|
3
|
+
*
|
|
4
|
+
* Pre-execution safety validation for Claude Code.
|
|
5
|
+
* Fail-closed design: if safety check fails, command is blocked.
|
|
6
|
+
*
|
|
7
|
+
* Full release coming soon.
|
|
8
|
+
*
|
|
9
|
+
* @see https://github.com/frmoretto/hardstop
|
|
10
|
+
*/
|
|
11
|
+
|
|
12
|
+
throw new Error(
|
|
13
|
+
'hardstop is a placeholder package. Full release coming soon. ' +
|
|
14
|
+
'See https://github.com/frmoretto/hardstop for updates.'
|
|
15
|
+
);
|
package/package.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "hardstop",
|
|
3
|
+
"version": "0.0.1",
|
|
4
|
+
"description": "The mechanical brake for AI-generated commands. Pre-execution safety validation for Claude Code.",
|
|
5
|
+
"main": "index.js",
|
|
6
|
+
"keywords": [
|
|
7
|
+
"hardstop",
|
|
8
|
+
"ai-safety",
|
|
9
|
+
"command-validation",
|
|
10
|
+
"security",
|
|
11
|
+
"claude-code",
|
|
12
|
+
"mcp",
|
|
13
|
+
"pre-execution",
|
|
14
|
+
"fail-closed",
|
|
15
|
+
"llm",
|
|
16
|
+
"bash",
|
|
17
|
+
"shell"
|
|
18
|
+
],
|
|
19
|
+
"author": "frmoretto <francesco.marinoni.moretto@gmail.com>",
|
|
20
|
+
"license": "CC-BY-4.0",
|
|
21
|
+
"repository": {
|
|
22
|
+
"type": "git",
|
|
23
|
+
"url": "git+https://github.com/frmoretto/hardstop.git"
|
|
24
|
+
},
|
|
25
|
+
"bugs": {
|
|
26
|
+
"url": "https://github.com/frmoretto/hardstop/issues"
|
|
27
|
+
},
|
|
28
|
+
"homepage": "https://github.com/frmoretto/hardstop"
|
|
29
|
+
}
|