agency-lang@0.37.0
The Agency language
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe reviewed execution and write paths serve the package’s audio, skill installation, and scheduling features and are invoked explicitly. Agent observability is configured for the package’s service; no malicious credential flow or automatic persistence was identified.
Decision evidence
public snapshot- The manifest exposes a library entry point and CLI binary; it declares no lifecycle hooks.
- The ffmpeg helper probes for ffmpeg and runs it to transcode speech audio into requested formats.
- Skill installation requires an explicit target flag and is performed by the `agency skills install` command.
- Launchd persistence is created through an explicit scheduler backend install operation.
- The flagged agent code configures observability for the agency-lang service using STATELOG_API_KEY.
Source & flagged code
7 flaggedPackage source references dynamic require/import behavior.
dist/lib/optimize/optimizerModule.jsView on unpkg · L32Source writes installer persistence such as shell profile or service configuration.
dist/lib/cli/schedule/backends/launchd.jsFindings
Affected versions and remediation
This report applies to agency-lang@0.37.0.
See all versions of agency-lang for other recorded verdicts.
- Review the evidence and your use of agency-lang@0.37.0 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.