hippo-memory@1.38.7
Biologically-inspired memory system for AI agents. Decay by default, strength through use.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThis is a guarded agent-integration package with automatic repair of a previously installed launcher wrapper. The source does not show credential theft, payload staging, self-dependency, or unconsented first-time install-time control-surface mutation.
Decision evidence
public snapshot- Installation runs a postinstall program.
- Postinstall automatically repairs an existing Codex launcher wrapper when its metadata exists.
- The explicit Codex hook command renames the real launcher and replaces it with a Hippo wrapper.
- The explicit Claude Code hook command writes commands into the agent settings file.
- Source text frames its behavior around supply-chain scanner reactions.
- The install path does not create a first-time Codex wrapper when metadata is absent.
- No runtime dependency on hippo-memory itself is declared.
- Reviewed prediction modules are ordinary local database storage code.
- Embedding network requests use configured provider API keys rather than install-time collection.
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/rerankers/cross-encoder.jsView on unpkg · L9Findings
Affected versions and remediation
This report applies to hippo-memory@1.38.7.
See all versions of hippo-memory for other recorded verdicts.
- Review the evidence and your use of hippo-memory@1.38.7 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.