agency-lang@0.18.1
The Agency language
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe required source paths show package-aligned operations, and package.json defines no install lifecycle hook. Static scanner hints do not establish an attack in the inspected code.
Decision evidence
public snapshot- package.json exposes a library entrypoint and an explicit agency CLI; its scripts are development and CLI tasks, with no install lifecycle hook.
- The optimizer writes only changed files from its source map after checking discovery-time hashes; this is an explicit optimizer operation.
- The IPC module forks a subprocess for a runtime session and applies output limits.
- OAuth token exchange posts to the provided token URL as part of its authentication flow.
- The CLI spawns Node to run compiled output with its resolver shim and sandbox flags.
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@0.18.1.
See all versions of agency-lang for other recorded verdicts.
- Review the evidence and your use of agency-lang@0.18.1 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.