hippo-memory@1.63.1
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe automatic repair of an existing Codex wrapper is a guarded integration lifecycle risk that warrants a warning. The inspected sources do not establish broad control-surface mutation or another concrete attack.
Decision evidence
public snapshot- package.json runs a package-local postinstall script.
- Postinstall attempts to repair an already installed Codex wrapper and prints setup guidance.
- The init detector recognizes existing agent configuration files; init is an explicit CLI flow.
- hippo setup detects integrations and supports dry-run; scheduling can be skipped.
- Workspace registration stores normalized project paths in the package registry.
- The daily schedule is configured through CLI setup code.
- The package has an install-time hook that can modify an existing Codex launcher wrapper, leaving a guarded integration risk.
Source & flagged code
8 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references a known benign dynamic code generation pattern.
dist/local-embedding.jsView on unpkg · L30Findings
Affected versions and remediation
This report applies to hippo-memory@1.63.1.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.63.1 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.