@copilotkit/runtime@1.75.2
<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 runtime code show ordinary package entrypoints, dependency loading, and configured service calls. The scanner hints do not establish malicious behavior.
Decision evidence
public snapshot- The manifest identifies the package and exposes built runtime entrypoints; it has no install lifecycle hook or wildcard dependency.
- The intelligence handler validates the runtime and request, resolves the user, then calls the configured annotation service.
- The flagged LangGraph entrypoint loads local modules and its declared LangGraph integration dependency.
- The resolver sends guardrail validation data to a base URL supplied by runtime configuration.
- The inspected source shows no credential harvesting, concealed exfiltration, persistence, destructive behavior, or install-time mutation.
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@1.75.2.
See all versions of @copilotkit/runtime for other recorded verdicts.
- Review the evidence and your use of @copilotkit/runtime@1.75.2 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.