aidd-kos

v0.2.1 suspicious
6.0
Medium Risk

Agentic Knowledge OS — LightRAG knowledge graph + MCP server for AI-driven development

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits potential risks due to its network calls and execution of external commands, combined with limited metadata and activity metrics.

  • Network calls that could be used for unauthorized data exchange
  • Execution of external commands without sufficient documentation
Per-check LLM notes
  • Network: Network calls to specific URLs may indicate legitimate functionality but could also be used for unauthorized data exchange.
  • Shell: Executing external commands suggests the package interacts with system tools, which is potentially risky if not properly controlled or documented.
  • Metadata: The repository is newly created with no activity metrics, and the maintainer's account details are sparse.

📦 Package Quality Overall: Medium (5.2/10)

✦ High Test Suite 9.0

Test suite present — 27 test file(s) found

  • Test runner config found: conftest.py
  • Test runner config found: pyproject.toml
  • 27 test file(s) detected (e.g. test_smoke.py)
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (4088 chars)
○ Low Contributing Guide 2.0

No contributing guide or governance files found

  • No CONTRIBUTING, CODE_OF_CONDUCT, or governance files found
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 136 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 5.0

Limited contributor diversity

  • 1 unique contributor(s) across 52 commits in spikestudio/aidd-kos
  • Single author but highly active (52 commits)

🔬 Heuristic Checks

⚠ Outbound Network Calls score 7.5

Found 5 network call pattern(s)

  • }).encode() req = urllib.request.Request( _LIGHTRAG_PAGINATED_URL,
  • try: with urllib.request.urlopen(req, timeout=30) as resp: data =
  • x_retries): req = urllib.request.Request( _LIGHTRAG_DELETE_URL,
  • try: req = urllib.request.Request(_LIGHTRAG_HEALTH_URL, method="GET")
  • d="GET") with urllib.request.urlopen(req, timeout=10) as resp: data =
✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

  • ep 2: mise install""" subprocess.run(["mise", "install"], cwd=self.project_dir, check=True)
  • """Step 3: uv sync""" subprocess.run(["uv", "sync"], cwd=self.project_dir, check=True) def i
  • xists(): result = subprocess.run( ["npx", "@colbymchenry/codegraph", "init",
  • ndex にフォールバック subprocess.run( ["npx", "@colbymchenry/codegraph", "ind
  • ) else: subprocess.run( ["npx", "@colbymchenry/codegraph", "index",
  • t server_running: subprocess.Popen( [ sys.executable,
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

No author email provided

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 5.0

Git history flags: Repository created very recently: 3 day(s) ago (2026-06-03T09:31:51Z)

  • Repository created very recently: 3 day(s) ago (2026-06-03T09:31:51Z)
  • Repository has zero stars and zero forks
⚠ Maintainer History score 6.0

3 maintainer concern(s) found

  • Package is very new: uploaded 2 day(s) ago
  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with aidd-kos 
Develop a fully-functional mini-application named 'KnowledgeBot' that leverages the Agentic Knowledge OS (aidd-kos) package to facilitate intelligent information retrieval and management. This application will serve as a personal knowledge manager, allowing users to store, query, and analyze data using AI-driven capabilities. Here’s a step-by-step guide on how to build 'KnowledgeBot':

1. **Setup Environment**: Begin by setting up your Python environment and installing the aidd-kos package.
2. **User Interface Design**: Design a simple yet intuitive user interface that allows users to interact with the system through natural language queries.
3. **Data Storage & Retrieval**: Utilize the LightRAG knowledge graph component of aidd-kos to store structured and unstructured data from various sources such as documents, web pages, and databases.
4. **Query Processing**: Implement a feature where users can input queries in natural language, and the application processes these queries using the MCP server provided by aidd-kos, returning relevant results.
5. **AI-Driven Analysis**: Enable the application to perform advanced analysis on the queried data, providing insights and summaries based on the retrieved information.
6. **Integration with External Tools**: Allow 'KnowledgeBot' to integrate with external tools like calendars, email clients, and note-taking apps for seamless data import/export.
7. **Security & Privacy**: Ensure all data interactions are secure and comply with privacy regulations.

Suggested Features:
- User authentication and role-based access control.
- Support for importing data from multiple formats (PDF, DOCX, CSV).
- Ability to schedule regular updates for stored data.
- Visualization of data insights through graphs and charts.
- Notification system for new data or updates.

By following these steps and incorporating the suggested features, you will create a powerful and user-friendly tool for managing and analyzing personal and professional information using the advanced functionalities of the aidd-kos package.

💬 Discussion Feed

Leave a comment

No discussion yet. Be the first to share your thoughts!