@bongos/core@1.19.900
Cloud Bongos — the AI-first build platform core (GDS + platform surfaces + module system), installed as a versioned dependency (ADR 0108).
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe source confirms an automatic devcontainer setup path that disables Claude Code permission prompts. This supports a warning for agent capability abuse, not a publish block, because it is not an npm install hook or demonstrated malicious attack chain.
Decision evidence
public snapshot- The devcontainer runs a setup script automatically after creation.
- That script changes the user-level Claude Code settings to bypass permission prompts.
- The script writes the changed settings back to disk.
- The package manifest declares no npm install lifecycle hook or self-dependency.
Source & flagged code
25 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@1.19.900.
See all versions of @bongos/core for other recorded verdicts.
- Review the evidence and your use of @bongos/core@1.19.900 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.