sdlc-agent-4-enterprise-server@1.45.0
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 27d ago · by lpm-firewall-aiThe published lifecycle is a no-op, and the potentially risky launcher download is explicitly gated rather than an install-time action. Static inspection found no concrete malicious chain.
Decision evidence
public snapshot- The only package lifecycle hook exits immediately.
- The separate launcher downloads Ollama only when the START_OLLAMA environment flag is enabled.
- Runtime configuration resolves its data directory from the workspace and configured data directory.
- Diagram export uses a cached local draw.io command with temporary input and output files supplied by its caller.
- The end-to-end setup isolates its data directory, and the Python mock helper only normalizes values.
- The required viewer files are identifiable bundled 3d-force-graph and Babel code.
- The standalone launcher contains an explicit opt-in shell download for Ollama.
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@1.45.0.
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@1.45.0 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.