agency-lang@0.19.1
The Agency language
AI Security Review
scanned 24d ago · by lpm-firewall-aiInspected source shows package features with explicit user-facing activation and safeguards, and the manifest lists no install lifecycle hook. The scanner hints map to ordinary runtime capabilities and do not establish malicious behavior.
Decision evidence
public snapshot- package.json exposes a CLI and runtime entrypoints; its listed scripts are development commands, with no install lifecycle hook shown.
- Workspace writeback is an explicit operation that checks source hashes and writes only changed files.
- The IPC runtime clamps user-supplied resource limits and uses subprocesses for runtime work.
- OAuth endpoints are required to use HTTPS, except for localhost development.
- Untrusted compiled output has a sandbox option that disables code generation from strings.
- Optimizer modules are user-authored, compiled, and loaded on request.
Source & flagged code
7 flaggedPackage source references child process execution.
dist/lib/optimize/workspace.jsView on unpkg · L6Findings
Affected versions and remediation
This report applies to agency-lang@0.19.1.
See all versions of agency-lang for other recorded verdicts.
- Review the evidence and your use of agency-lang@0.19.1 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.