sdlc-agent-4-enterprise-server@1.53.1
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 8d ago · by lpm-firewall-aiSource inspection found no malicious behavior: lifecycle scripts do not run an install-time payload, credentialed Pega requests use caller-supplied credentials and endpoint values, and command execution is exposed through an explicit sandbox tool. Scanner findings correspond to test setup, local tool integrations, and bundled library code.
Decision evidence
public snapshot- package.json points the package entrypoint and executable to dist/index.js; prepublishOnly builds and prepare exits immediately.
- The indicated auth and Pega locations are application route handlers mounted by the server. The Pega fetch handler requires request-supplied credentials and a caller-supplied endpoint.
- Shell execution is exposed as an explicit sandbox tool taking a command argument; the executor applies configured timeouts, and local mode is an intentional fallback.
- The flagged test setup uses an isolated temporary directory; the Python fixture only normalizes values, and LLM model discovery targets its configured server.
- Draw.io handling searches for a local executable, while the bundled 3D graph file identifies itself as a library.
Source & flagged code
14 flagged · loading sourcePackage source references dynamic require/import behavior.
test-index.cjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to sdlc-agent-4-enterprise-server@1.53.1.
See all versions of sdlc-agent-4-enterprise-server for other recorded verdicts.
- Review the evidence and your use of sdlc-agent-4-enterprise-server@1.53.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.