@aspectlylabs/mikka@0.0.278
Local Mikka daemon: runs agents through the user's own CLIs
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package uses credentials and subprocesses for its stated local agent and provider integration features. The reviewed broker validates HTTPS destinations and forwards requests to the configured provider or Anthropic/OpenAI defaults; no unrelated credential destination or malicious automatic behavior was found.
Decision evidence
public snapshot- The manifest defines a CLI and module entry points but no lifecycle scripts.
- Provider credentials are checked for HTTPS URLs and passed to the matching configured provider.
- The API key broker forwards requests to the configured provider URL or the Anthropic and OpenAI API defaults.
- The computer driver helper checks an existing local binary's version when called.
- No source reviewed showed credentials being redirected to an unrelated fixed host.
- The credential and shell execution findings fit the package's agent and provider integration features.
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@0.0.278.
See all versions of @aspectlylabs/mikka for other recorded verdicts.
- Review the evidence and your use of @aspectlylabs/mikka@0.0.278 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.