claude-recall@0.42.1
Persistent memory for Claude Code and Pi with native Skills integration, automatic capture, failure learning, and project scoping
AI Security Review
scanned 23d ago · by lpm-firewall-aiStatic source inspection establishes automatic agent hook migration during installation, constrained to existing claude-recall commands. The first-party extension lifecycle policy supports a warning; the inspected behavior does not justify blocking as malware.
Decision evidence
public snapshot- package.json automatically runs scripts/postinstall.js during installation.
- The install script invokes repair with automatic approval and all scopes.
- The CLI forwards automatic approval and scope to the repair implementation.
- Repair scans user and project agent settings throughout the home directory.
- Changes are restricted to broken or incompatible existing claude-recall hook commands and preserve backups.
- The inspected repair path does not install absent hooks or replace unrelated hook entries.
- MCP consolidation is separately gated by the explicit doctor --fix command.
- No credential exfiltration or remote payload execution was established in the inspected path.
Source & flagged code
20 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 unpkgFindings
Affected versions and remediation
This report applies to claude-recall@0.42.1.
See all versions of claude-recall for other recorded verdicts.
- Review the evidence and your use of claude-recall@0.42.1 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.