agency-lang@0.19.3
The Agency language
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the inspected flagged code supports ordinary runtime, OAuth, and local model-serving functions. No concrete malicious attack surface was established.
Decision evidence
public snapshot- package.json defines development and test commands; it contains no install lifecycle hook.
- The flagged workspace module manages an in-memory cache identity counter.
- The IPC module runs subprocess execution segments as part of the runtime.
- OAuth token exchange uses the package's HTTP helper to send an authorization-code request.
- The CLI starts Node with generated output and runtime arguments.
- Local model serving starts Python with inherited environment and offline mode enabled.
Source & flagged code
8 flaggedPackage source references child process execution.
dist/lib/optimize/workspace.jsView on unpkg · L6Findings
Affected versions and remediation
This report applies to agency-lang@0.19.3.
See all versions of agency-lang for other recorded verdicts.
- Review the evidence and your use of agency-lang@0.19.3 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.