@aspectlylabs/mikka@0.0.413
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe package's credential broker sends model keys to the configured HTTPS provider or official API defaults, with restricted routes and redirects disabled. The flagged process execution and network activity fit the daemon's agent-running purpose, and the reviewed runtime filters credential-like environment values.
Decision evidence
public snapshot- The manifest exposes a daemon CLI and module entry points.
- Provider credentials accept only HTTPS base URLs without embedded user info, queries, or fragments.
- The API-key broker uses the configured provider URL or official Anthropic/OpenAI defaults, limits forwarded routes, and refuses redirects.
- The native runtime rejects credential-like environment variables and accepts model or OAuth tokens only as placeholders, then removes the OAuth token.
- The package uses child processes and network requests, but the inspected code ties them to running agent CLIs, provider requests, and daemon features.
- A configured third-party provider can receive the user's API key; the source validates HTTPS and routes the key to that configured provider rather than a fixed unofficial gateway.
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@0.0.413.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.413 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.