@aspectlylabs/mikka@0.0.396
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe flagged credential and network flows are consistent with running agents using a selected model provider. The broker limits forwarded requests to model API paths, and the inspected source shows no malicious collection or unrelated credential transfer.
Decision evidence
public snapshot- The manifest describes a local daemon that runs agents through the user's CLIs and lists its CLI and module entry points.
- Run credentials accept only HTTPS provider URLs without embedded username or password; standard API-key runs use the Anthropic or OpenAI API endpoints.
- The local API-key broker limits requests to specific model API paths and forwards the key with those requests.
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@0.0.396.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.396 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.