agentseal 0.3.1 → 0.3.2

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.
Files changed (2) hide show
  1. package/README.md +15 -4
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -225,7 +225,7 @@ The open source scanner covers 173 probes. [AgentSeal Pro](https://agentseal.org
225
225
 
226
226
  [Start scanning at agentseal.org](https://agentseal.org)
227
227
 
228
- ## NEW: `agentseal guard` (Python CLI)
228
+ ## `agentseal guard` - Machine Security Scan (Python CLI)
229
229
 
230
230
  One command scans your entire machine for AI agent threats. No config, no API keys needed.
231
231
 
@@ -234,16 +234,27 @@ pip install agentseal
234
234
  agentseal guard
235
235
  ```
236
236
 
237
- - Auto-discovers **17 AI agents** (Claude, Cursor, VS Code, Windsurf, Cline, Roo Code, Zed, and more)
237
+ - Auto-discovers **17 AI agents** (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Gemini CLI, Codex, Cline, Roo Code, Zed, and more)
238
238
  - Scans every **skill/rules file** for malware, credential theft, prompt injection, reverse shells
239
239
  - Audits every **MCP server config** for sensitive path access, hardcoded API keys, broad permissions
240
+ - Detects **toxic data flows** across MCP servers (e.g. filesystem + slack = data exfiltration risk)
241
+ - Tracks **MCP server baselines** to catch supply chain / rug pull attacks
240
242
  - Red/yellow/green results with numbered action items
241
243
 
244
+ ## `agentseal shield` - Continuous Monitoring (Python CLI)
245
+
246
+ Watches your skill directories and MCP configs in real time. Sends desktop notifications on threats.
247
+
242
248
  ```bash
243
- # Also available: prompt injection scanner
244
- agentseal scan --prompt "You are a helpful assistant" --model gpt-4o
249
+ pip install agentseal[shield]
250
+ agentseal shield
245
251
  ```
246
252
 
253
+ - Watches all 17 agent config paths automatically
254
+ - Debounces rapid file changes (editors, git operations)
255
+ - Native desktop notifications (macOS, Linux)
256
+ - Runs baseline + toxic flow checks on every MCP config change
257
+
247
258
  [View Python package on PyPI](https://pypi.org/project/agentseal/)
248
259
 
249
260
  ## Links
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agentseal",
3
- "version": "0.3.1",
3
+ "version": "0.3.2",
4
4
  "description": "Security validator for AI agents — 191 attack probes to test prompt injection and extraction defenses",
5
5
  "type": "module",
6
6
  "main": "./dist/index.cjs",