@aspectlylabs/mikka@0.0.320
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged process execution, credential handling, and network access fit this package's stated purpose of running agents through the user's CLIs. The reviewed flows are run-scoped and directed to the selected provider or trusted Mikka endpoint; no unrelated collection or install-time behavior was found.
Decision evidence
public snapshot- The manifest describes a local daemon that runs agents through the user's own CLIs and has no lifecycle scripts.
- The model API broker is created for an approved run and forwards credentials only to the configured provider over HTTPS; default destinations are api.anthropic.com and api.openai.com.
- GitHub credentials are obtained through a trusted Mikka run endpoint and used for GitHub repository operations.
- The flagged process execution and network access support the package's stated agent-running purpose.
- The model broker limits requests to provider API paths, rejects redirects, and removes its temporary key when closed.
- The GitHub credential exchange uses a run token and rejects untrusted endpoint hosts.
Source & flagged code
6 flaggedPackage source references child process execution.
github-credentials.mjsView on unpkg · L7Findings
Affected versions and remediation
This report applies to @aspectlylabs/mikka@0.0.320.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.320 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.