hippo-memory@1.68.0
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 flagged agent configuration and persistence behaviors are user-command driven and aligned with the package’s integration features, rather than hidden in npm installation. Because `hippo init` can modify agent configuration and schedule recurring work, classify it as a warning-level agent capability.
Decision evidence
public snapshot- `hippo init` automatically installs detected agent integrations and a daily schedule unless the user disables them.
- The integrations patch existing agent instruction files and add user-level hooks for detected agents.
- The postinstall hook repairs an existing Codex wrapper and prints setup suggestions; it does not install agent hooks.
- The daily schedule runs Hippo maintenance against registered workspaces.
- The agent configuration and scheduling changes are reached through the explicit `hippo init` command, not the npm install hook.
- The package offers `--no-hooks`, `--no-schedule`, and `HIPPO_SKIP_AUTO_INTEGRATIONS` controls.
Source & flagged code
9 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@1.68.0.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.68.0 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.