hippo-memory@2.1.0
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe postinstall behavior is limited to setup guidance and repair of a Codex wrapper already recorded as opted in. Agent integration and daily scheduling occur through the explicit init command, so the inspected scanner signals do not establish malicious behavior.
Decision evidence
public snapshot- package.json declares a postinstall hook that runs scripts/postinstall.cjs.
- The postinstall module checks for existing agent installations, prints setup instructions, and only repairs a Codex wrapper when prior opt-in metadata exists.
- The init command detects project agent files before adding integrations; its Codex integration offers an install command, while other hooks are installed through init.
- The compaction spool uses local files to store and replay compaction summaries.
- Daily scheduling is initiated by hippo init and can be skipped with --no-schedule or HIPPO_SKIP_SCHEDULE=1.
- The package has a postinstall lifecycle hook that imports dist/postinstall.js.
- The init flow can write agent configuration and create a daily schedule, but those actions are tied to an explicit CLI command.
Source & flagged code
5 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 dynamic require/import behavior.
dist/embeddings/transformers.jsView on unpkg · L6Findings
Affected versions and remediation
This report applies to hippo-memory@2.1.0.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@2.1.0 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.