sdlc-agent-4-enterprise-server@1.30.0
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 lifecycle behavior, payload staging, credential theft, or covert control-surface modification. The notable installer is an explicitly environment-gated application-start path outside the npm entrypoint.
Decision evidence
public snapshot- No npm preinstall/install/postinstall hook is declared.
- Published bin/main points to dist/index.js, which initializes the MCP server only when invoked.
- Dynamic imports in the server are local migration modules; no remote payload loader found.
- Credential-looking values are test fixtures, not harvested secrets.
- start.js's curl-piped installer is gated by START_OLLAMA=true and is not an npm entrypoint.
- Runtime server legitimately reads configured workspace data and starts HTTP/MCP services.
- The separately shipped start.js can write user configuration and spawn local services when explicitly run.
- Network/provider integrations and WASM parsers are consistent with the advertised code-intelligence/MCP application.
Source & flagged code
29 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@1.30.0.
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@1.30.0 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.