@melandlabs/opencontext@0.12.0
OpenContext — single-package facade that bundles the contracts, memory-store, retrieval, loop engine, and agent runtime. Install once, get every capability.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and inspected entrypoints show application functionality without a confirmed attack chain. The scanner hints about large bundles, networking, and environment access do not establish malicious behavior.
Decision evidence
public snapshot- package.json has no preinstall, install, or postinstall hook; its scripts are build, typecheck, lint, and tests.
- The CLI dispatches operations from explicit command-line arguments.
- The MCP server starts only when the CLI is invoked with no command or with the mcp command.
- The library entrypoint imports application and platform modules; no attack behavior was established from the inspected entrypoint.
Source & flagged code
4 flagged · loading sourcePackage contains source files above the normal full-analysis size ceiling.
dist/index.jsView on unpkgPackage contains an oversized executable-looking CLI entrypoint.
dist/cli/opencontext.jsView on unpkgThe CLI dispatches operations from explicit command-line arguments.
Findings
Affected versions and remediation
This report applies to @melandlabs/opencontext@0.12.0.
See all versions of @melandlabs/opencontext for other recorded verdicts.
- Review the evidence and your use of @melandlabs/opencontext@0.12.0 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.