hippo-memory@1.52.1
Biologically-inspired memory for AI agents. Zero runtime deps, SQLite, MCP server, and an opt-in hosted TypeSafe Jev reranker. Decay, retrieval strengthening, consolidation.
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource inspection found that postinstall repair is limited to a previously opted-in Codex wrapper, while other agent setup is user-invoked. The inspected module excerpts show package-aligned functionality and no concrete malicious behavior.
Decision evidence
public snapshot- The postinstall repair runs only when wrapper metadata already records user opt-in; a first install requires an explicit CLI command.
- The installer’s Claude Code message is a read-only nudge that directs users to run setup themselves.
- Project hook installation is reached through the explicit `hippo init` flow.
- The capture code checks Claude project files to locate session data; this excerpt shows no transfer or configuration write.
- OpenCode plugin installation is exposed as a setup API.
- The embedding provider and prediction module excerpts describe package-aligned embedding and tenant-scoped data behavior.
Source & flagged code
7 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/embeddings.jsView on unpkg · L99Findings
Affected versions and remediation
This report applies to hippo-memory@1.52.1.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.52.1 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.