@bongos/core@1.20.11
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 scanner’s runtime hints resolve to request metrics and local skill linting. The remaining concern is the explicit CLI flow that writes agent skills and permissions, which warrants a warning for agent capability setup but does not establish malicious install-time behavior.
Decision evidence
public snapshot- The manifest has CLI and server entrypoints but no npm lifecycle scripts.
- The explicit init and upgrade CLI commands invoke agent materialization.
- Materialization copies enabled module skills into the instance’s .claude/skills directory and writes starter command permissions in .claude/settings.json.
- The flagged runtime code counts HTTP requests and lints edited skill files; it does not perform the indicated account action.
- Other inspected integration locations concern local worktree or transcript paths, generated module documentation, and review rules.
- There is no package install hook that automatically changes agent configuration.
- The starter settings grant command permissions and are produced by the explicit CLI setup flow.
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@1.20.11.
See all versions of @bongos/core for other recorded verdicts.
- Review the evidence and your use of @bongos/core@1.20.11 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.