@aspectlylabs/mikka@0.0.428
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 16h ago · by lpm-firewall-aiThe flagged process and network operations serve the package’s stated purpose of running coding agents and handling authorized GitHub tasks. The reviewed credential flows use configured service endpoints or official provider defaults; no unrelated credential collection or exfiltration was found.
Decision evidence
public snapshot- The manifest exposes a daemon library and CLI and declares no lifecycle scripts.
- The API-key broker uses official Anthropic and OpenAI endpoints by default; custom provider URLs come from the supplied credential configuration and must use HTTPS.
- The broker forwards API requests and keys to that configured origin, rejecting redirects.
- The GitHub helper exchanges a run token with a configured endpoint; GitHub credentials are used for GitHub operations.
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@0.0.428.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.428 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.