sdlc-agent-4-enterprise-server@1.53.12
Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe source confirms a caller-invoked command execution capability whose local mode has reduced isolation and inherits process environment values. That supports a warning for dangerous capability, while the inspected paths do not establish malicious execution or credential exfiltration.
Decision evidence
public snapshot- The LLM error helper summarizes nested connection errors; the inspected receiver does not establish a separate attack.
- The sandbox exposes command execution through a named tool, and its handler passes the caller’s command to the execution manager.
- Non-Linux systems default to local mode unless full isolation is enabled; local fallback is enabled by default.
- If Docker is unavailable, a requested Docker session can fall back to local execution.
- The local executor passes process environment values and runs the supplied command through a shell.
- The package prepare hook exits successfully without other work.
- Command execution requires a caller to invoke the sandbox tool; the inspected paths do not show hidden or automatic command execution.
- The inspected credential references are for local test requests and credentials supplied per request to the Pega route; they do not establish an unrelated credential recipient.
Source & flagged code
19 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@1.53.12.
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@1.53.12 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.