hippo-memory@1.65.0
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 install lifecycle path inspected does not establish unconsented agent configuration changes, while the agent setup and scheduling behaviors are reached through explicit CLI commands. The inspected behavior is consistent with the package's memory integration and maintenance functions, so the scanner signals do not establish maliciousness.
Decision evidence
public snapshot- The manifest's install hook runs a local postinstall script.
- The inspected postinstall entry returns when disabled and describes its Codex action as repair-only for an existing wrapper.
- The init path checks for existing agent configuration files before selecting integrations.
- Init has a flag that skips its agent configuration writes.
- The setup behavior is exposed through the explicit hippo setup command.
- Workspace registration saves project paths to the registry.
- The daily runner is created by the scheduling helper using the global store path.
- The package has a postinstall hook and can create a scheduled daily runner, but the inspected runner setup is invoked from CLI setup flows.
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 · L31Findings
Affected versions and remediation
This report applies to hippo-memory@1.65.0.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.65.0 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.