@constellationdev/mcp@1.2.10
Codebase Understanding for AI Coding Agents
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe active telemetry path exposes a service credential to an unrestricted configurable destination, warranting a warning under the credential-forwarding policy. The inspected execution and lifecycle behavior does not establish malware or justify blocking publication.
Decision evidence
public snapshot- The active entrypoint reads the Constellation access key from the environment.
- Usage telemetry accepts USAGE_ENDPOINT_URL without restricting its destination.
- Telemetry sends the access key as bearer authentication to the selected endpoint.
- Successful code queries with API invocations activate telemetry using the existing access key.
- Usage tracking defaults to enabled and supports environment-based disabling.
- No package-controlled unrelated recipient or covert credential harvesting was established.
- Child process execution runs the bundled sandbox worker for caller-supplied queries.
- The manifest has a Husky prepare hook, no install hooks, and no runtime self-dependency.
Source & flagged code
4 flaggedA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/index.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @constellationdev/mcp@1.2.10.
See all versions of @constellationdev/mcp for other recorded verdicts.
- Review the evidence and your use of @constellationdev/mcp@1.2.10 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.