sdlc-agent-4-enterprise-server@1.53.0
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe source exposes a host-shell execution capability without isolation, with local fallback enabled, so a warning is warranted. The inspected lifecycle scripts do not show install-time attack behavior, and no separate malicious action was established.
Decision evidence
public snapshot- The local executor runs supplied commands through the host shell and its source describes it as having no isolation.
- The execution manager can route a Docker request to local execution when Docker is unavailable; local fallback defaults to enabled.
- Execution is activated by calling the sandbox execution method, which can create an ephemeral session for the command.
- The manifest's prepare script exits immediately, while prepublishOnly runs the build.
- Host command execution is an explicit runtime sandbox feature, rather than install-time or background activity.
- The inspected source establishes a dangerous execution capability but no separate malicious command, payload, or data transfer.
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@1.53.0.
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@1.53.0 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.