🤖 AI Analysis

Final verdict: SUSPICIOUS

The package is flagged as suspicious due to the potential misuse of shell execution, which could allow for unintended actions. However, it does not present immediate threats like network risks or credential harvesting.

Shell risk identified due to potential execution of external commands
Low activity of the maintainer's PyPI account

Per-check LLM notes

Network: No network calls were detected.
Shell: The presence of shell execution suggests the package may perform tasks outside of its main functionality, which could be legitimate but warrants further investigation into the specific commands and their purposes.
Obfuscation: No obfuscation patterns detected, indicating low risk.
Credentials: No credential harvesting patterns detected, indicating low risk.
Metadata: The maintainer has only one package on PyPI, which could indicate a new or less active account.

📦 Package Quality Overall: Medium (5.6/10)

✦ High Test Suite 9.0

Test suite present — 18 test file(s) found

Test runner config found: pyproject.toml
18 test file(s) detected (e.g. test_cli.py)

◈ Medium Documentation 5.0

Some documentation present

Detailed PyPI description (5834 chars)

○ Low Contributing Guide 4.0

No contributing guide or governance files found

Development Status classifier >= Beta

◈ Medium Type Annotations 5.0

Partial type annotation coverage

77 type-annotated function signatures detected in source

◈ Medium Multiple Contributors 5.0

Limited contributor diversity

1 unique contributor(s) across 56 commits in xomyachok-shaolin/anamnestic
Single author but highly active (56 commits)

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 10.0

Found 5 shell execution pattern(s)

nd(path) try: r = subprocess.run(argv, capture_output=True, text=True, timeout=timeout) e
se else "0", ) proc = subprocess.run( [sys.executable, "-m", _MODULE, "embed-worker"],
se else "0", ) proc = subprocess.run( [sys.executable, "-m", _MODULE, "reindex-worker"],
eer, "true", ] return subprocess.run(cmd, capture_output=True, timeout=timeout + 5).returncode ==
src, dst, ] proc = subprocess.run(cmd, capture_output=True, text=True, timeout=600) files

✓ 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

Repository xomyachok-shaolin/anamnestic appears legitimate

⚠ Maintainer History score 2.0

1 maintainer concern(s) found

Author "xomyachok-shaolin" 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 anamnestic

Create a Python-based command-line interface (CLI) tool named 'AIRecall' using the 'anamnestic' package. This tool will enable users to interact with AI models such as Claude and ChatGPT in a persistent session where the history of interactions is stored and searchable. The goal is to enhance the user experience by allowing them to recall previous queries and responses quickly and efficiently.

### Features:
1. **Persistent Session:** Users should be able to start a session with an AI model, and their interaction history should be saved across multiple runs of the CLI.
2. **Hybrid Search:** Implement a search feature that allows users to search through their interaction history using keywords. This feature should support both exact matches and fuzzy searches.
3. **Turn-Based Interaction Logging:** Each query-response pair should be logged in a structured format (JSONL), making it easy to manage and search.
4. **Customizable AI Model Integration:** Allow users to configure the CLI to work with different AI models by specifying the API endpoint and any required authentication details.
5. **Session Management:** Provide commands to start, stop, and resume sessions.
6. **Export/Import Sessions:** Enable users to export their session data to a file and import previously exported data into a new session.
7. **Interactive Help:** Include a help command that explains how to use each feature of the CLI.

### Utilization of 'anamnestic':
- Use 'anamnestic' to handle the persistence and hybrid search capabilities of the user's interaction history. Specifically, leverage its ability to store and retrieve past queries and responses in a searchable manner.
- Integrate 'anamnestic' seamlessly into the CLI workflow so that every time a user interacts with an AI model, the interaction is logged and can be recalled using the search functionality provided by 'anamnestic'.
- Ensure that the CLI tool is designed to be user-friendly, efficient, and robust, providing a seamless experience for users who want to interact with AI models in a persistent and organized way.