hippo-memory@1.63.2
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 package has an explicit CLI path that modifies agent configuration, which warrants a warning under the agent capability policy. Its npm postinstall is limited to repairing an existing opted-in wrapper and printing setup guidance, so the inspected sources do not support blocking it as an install-time control hijack.
Decision evidence
public snapshot- Running `hippo init` invokes automatic agent integration setup unless the user disables it.
- The integration detects existing agent markers and may patch their instruction files and install user-level hooks.
- The postinstall routine is limited to repairing an already-installed Codex wrapper and printing setup nudges.
- The scheduler’s daily maintenance runs Hippo commands in registered workspaces containing `.hippo`.
- The postinstall script does not install first-time agent configuration; the configuration changes are reached through the CLI init command.
- Instruction-file patching skips files that do not already exist.
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 · L30Findings
Affected versions and remediation
This report applies to hippo-memory@1.63.2.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.63.2 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.