sdlc-agent-4-enterprise-server@1.42.1
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package is not an install-time malware chain, but its exposed MCP capability permits host shell execution with an unsafe local default and fallback. This is a material dangerous capability requiring a warning.
Decision evidence
public snapshot- Its MCP sandbox tool accepts a caller-supplied command and sends it to the execution manager.
- On macOS and Windows, local execution is the default; Docker unavailability also falls back to local execution.
- The local executor inherits the server environment and runs commands through Bash or cmd.exe on the host.
- No preinstall, install, or postinstall hook exists; prepare only exits successfully.
- The flagged credential strings are detector test fixtures, and the Python fixture only normalizes data.
- No package self-dependency or automatic installer chain was found.
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@1.42.1.
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@1.42.1 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.