@bongos/core@1.20.53
Cloud Bongos — the AI-first build platform core (GDS + platform surfaces + module system), installed as a versioned dependency (ADR 0108).
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package-owned agent setup is a real capability and warrants a warning, but it is triggered by explicit CLI setup and the starter settings are permissions-only. The inspected runtime findings do not establish account actions or another concrete attack.
Decision evidence
public snapshot- The package exposes a bongos CLI; its manifest has no install lifecycle script.
- The init path calls a materializer that writes project-local Claude settings when needed.
- The starter settings add permissions for Bongos commands; upgrade also runs the materializer.
- The skill-lint hook checks a changed skill file and prints local warnings; its CLI entry runs only when invoked directly.
- The starter settings are permissions-only and add no hooks.
- The inspected runtime locators show route normalization and local lint output, not account actions.
Source & flagged code
23 flagged · loading sourcePackage contains a critical-looking secret pattern.
tests/public_mirror_export.mjsView on unpkg · L103AWS access key ID in tests/public_mirror_export.mjs
tests/public_mirror_export.mjsView on unpkg · L103Findings
Affected versions and remediation
This report applies to @bongos/core@1.20.53.
See all versions of @bongos/core for other recorded verdicts.
- Review the evidence and your use of @bongos/core@1.20.53 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.