sdlc-agent-4-enterprise-server@1.23.0
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe suspicious primitives are package-aligned, user-invoked features or an optional container launcher, not install-time or covert behavior. Source inspection found no concrete malicious chain.
Decision evidence
public snapshot- Runtime can download a hashed native SQLite binding.
- start.js has a START_OLLAMA-gated shell installer.
- Web module exposes user-invoked fetch/download/API tools.
- package.json has no preinstall/install/postinstall hook.
- Bin entry is dist/index.js; no import-time installer found.
- Native download uses a fixed GitHub URL and SHA-256 verification.
- Web tools are explicit MCP capabilities with SSRF checks and workspace-bound downloads.
- No credential harvesting, exfiltration, stealth persistence, or agent-config writes found.
- Test secret finding is synthetic credential-detector input.
Source & flagged code
17 flagged · loading sourcePackage contains a critical-looking secret pattern.
dist/modules/memory/masking/__tests__/CredentialDetector.test.jsView on unpkg · L11GitHub personal access token in dist/modules/memory/masking/__tests__/CredentialDetector.test.js
dist/modules/memory/masking/__tests__/CredentialDetector.test.jsView on unpkg · L11Findings
Affected versions and remediation
This report applies to sdlc-agent-4-enterprise-server@1.23.0.
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@1.23.0 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.