@aspectlylabs/mikka@0.0.310
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged process execution is consistent with a daemon that runs agent CLIs. The inspected credential flow uses a configured or standard model provider endpoint, restricts requests, and rejects redirects; no malicious behavior was found.
Decision evidence
public snapshot- The package describes itself as a local daemon that runs agents through the user's own CLIs and exposes module and CLI entry points.
- A run requires tool approval before its assigned model credential is used.
- The credential broker routes to the configured provider URL or the standard Anthropic/OpenAI API URL, and disables redirects.
- The broker accepts only protocol-specific model request paths; the native runner sends model traffic through its local broker socket.
Source & flagged code
6 flaggedPackage source references child process execution.
github-credentials.mjsView on unpkg · L4Findings
Affected versions and remediation
This report applies to @aspectlylabs/mikka@0.0.310.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.310 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.