🤖 AI Analysis

Final verdict: SAFE

The package shows minimal risks across various checks and does not exhibit signs of malicious intent or supply-chain attacks.

No network or shell risks that could lead to external compromise.
Maintainer metadata quality is low but does not indicate malicious behavior.

Per-check LLM notes

Network: No network calls detected, indicating minimal external risk.
Shell: Shell executions appear to be for local command execution related to scanning and inspection, which aligns with the package's presumed functionality.
Obfuscation: No obfuscation patterns detected, indicating low risk.
Credentials: No credential harvesting patterns detected, indicating low risk.
Metadata: The maintainer seems new and there's low metadata quality, but no clear malicious indicators.

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

import subprocess proc = subprocess.run( ["agent-readiness", "scan-repo", path, "--json", "-
import subprocess proc = subprocess.run( ["agent-readiness", "scan-monorepo", path, "--json"
import subprocess proc = subprocess.run( ["agent-readiness", "scan-workspace", path, "--json
import subprocess proc = subprocess.run( ["agent-readiness", "inspect", path, "--json"],
dren), "--no-open", ] subprocess.Popen( cmd, stdout=subprocess.DEVNULL, std
tr(SCANNER_SRC) cli_raw = subprocess.check_output( [sys.executable, "-m", "agent_readiness.cli",

✓ 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

No GitHub repository linked

No GitHub repository link found

⚠ Maintainer History score 4.0

2 maintainer concern(s) found

Author "Harry Dai" appears to have only 1 package on PyPI (new or inactive account)
Package has no PyPI classifiers (low effort / metadata quality)

✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with agent-readiness-mcp

Create a Python-based mini-application named 'CodeGuard' which leverages the 'agent-readiness-mcp' package to ensure coding agents are ready for deployment in a production environment. CodeGuard should have a user-friendly interface where users can input details about their coding agents, such as agent type, version, and deployment environment. The application will then perform a readiness scan to check if the agent meets all necessary requirements for deployment. If any issues are detected, CodeGuard should provide detailed feedback on what needs to be fixed before the agent can be deployed safely. Additionally, the app should offer an 'Apply Fixes' feature that automatically applies the necessary corrections based on the scan results. Users should also be able to schedule regular scans for ongoing maintenance of their coding agents. Utilize the 'agent-readiness-mcp' package to handle the scanning, detection, and applying processes, ensuring seamless integration and efficient operation.