@copilotkit/runtime@1.76.0
<img src="https://github.com/user-attachments/assets/0a6b64d9-e193-4940-a3f6-60334ac34084" alt="banner" style="border-radius: 12px; border: 2px solid #d6d4fa;" />
AI Security Review
scanned 27d ago · by lpm-firewall-aiThe manifest and inspected entrypoint behavior are consistent with a CopilotKit runtime library, with no install hook or demonstrated malicious behavior. The scanner’s dynamic-loading hint resolves to static module requires in the inspected LangGraph entrypoint.
Decision evidence
public snapshot- The package exposes compiled runtime entrypoints and its scripts show no install lifecycle hook.
- The intelligence handler requires a configured CopilotKit runtime, resolves the user, and forwards request annotation fields to that runtime’s intelligence client.
- The guardrails resolver sends conversation messages and configured allow/deny topics to a validation endpoint as part of its resolver flow.
- The flagged LangGraph file uses static requires for package modules and its optional integration; the dynamic-require hint was not supported by the inspected match.
Source & flagged code
3 flaggedPackage source references dynamic require/import behavior.
dist/langgraph.cjsView on unpkg · L1Package metadata claims a different repository identity while copied source loads a runtime dependency bridge.
dist/v2/runtime/handlers/intelligence/annotate.cjsView on unpkg · L6Findings
Affected versions and remediation
This report applies to @copilotkit/runtime@1.76.0.
See all versions of @copilotkit/runtime for other recorded verdicts.
- Review the evidence and your use of @copilotkit/runtime@1.76.0 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.