sdlc-agent-4-enterprise-server@1.38.0
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 2mo ago · by lpm-firewall-aiDirect inspection found no malicious install hook, secret harvesting, exfiltration, or foreign AI-agent control-surface mutation. Static hints primarily point to fixtures, bundled vendor code, and intended server functionality.
Decision evidence
public snapshot- Unreferenced start.js can fetch and execute Ollama's installer, but only when explicitly run with START_OLLAMA enabled.
- package.json has no preinstall, install, or postinstall hook; prepublishOnly is publish-time only.
- The declared bin/main is dist/index.js, which initializes the MCP/HTTP server rather than importing start.js.
- The opt-in installer is guarded by START_OLLAMA and checks for an existing local runtime.
- The flagged Python file is a simple test normalizer; the JWT/password strings are detector test fixtures.
- No inspected source showed credential harvesting, foreign agent-config mutation, or exfiltration endpoint.
Source & flagged code
30 flagged · loading sourcePackage contains a critical-looking secret pattern.
src/modules/memory/masking/__tests__/CredentialDetector.test.tsView on unpkg · L14GitHub personal access token in src/modules/memory/masking/__tests__/CredentialDetector.test.ts
src/modules/memory/masking/__tests__/CredentialDetector.test.tsView on unpkg · L14Findings
Affected versions and remediation
This report applies to sdlc-agent-4-enterprise-server@1.38.0.
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@1.38.0 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.