@copilotkit/runtime@1.70.2
<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 2mo ago · by lpm-firewall-aiNo concrete malicious behavior was found. The remaining risk is runtime transmission of application data to configured cloud services and incomplete static coverage, not an install-time compromise.
Decision evidence
public snapshot- The manifest declares side-effectful runtime entrypoints.
- The annotation handler forwards a caller-supplied payload after resolving the authenticated intelligence user.
- When cloud guardrails are enabled, the resolver sends conversation content to the configured cloud endpoint.
- No preinstall, install, or postinstall hook is present in the manifest.
- The observed network calls are runtime features gated by configured cloud or intelligence use, not install-time behavior.
- No source inspected performs filesystem harvesting, shell execution, persistence, or destructive actions.
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@1.70.2.
See all versions of @copilotkit/runtime for other recorded verdicts.
- Review the evidence and your use of @copilotkit/runtime@1.70.2 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.