hippo-memory@1.52.8
Memory for AI agents that learns what is wrong and stops repeating it. MCP server and hooks for Claude Code, Codex and Cursor. SQLite, zero runtime deps.
AI Security Review
scanned 14d ago · by lpm-firewall-aiInspected source shows a guarded, repair-only postinstall path and CLI-exposed agent integration. The static warnings do not establish malicious behavior.
Decision evidence
public snapshot- The postinstall entry invokes a small wrapper that imports the compiled postinstall module.
- The postinstall module attempts wrapper repair; repair returns without changing anything when no prior wrapper metadata exists.
- Repair is limited to an existing opted-in Codex wrapper, while integration installation is exposed through the CLI.
- Capture code reads the user's Claude project directory as local input; inspected code shows no network send there.
- The embedding provider uses an API-backed embedding path, consistent with the package's stated embedding functionality.
Source & flagged code
6 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@1.52.8.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.52.8 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.