koragraphmcp@0.1.5
Local multi-repo code-graph MCP server
AI Security Review
scanned 11d ago · by lpm-firewall-aiSource inspection shows project-scoped agent configuration writes through explicit commands, which warrant a capability warning. The postinstall action is limited to copying a missing guide, and no concrete malicious behavior was established.
Decision evidence
public snapshot- The explicit practice sync command can write agent instruction files, including an AGENTS.md file created even when absent.
- The package offers a command that adds its own hooks to a project’s Claude Code settings.
- The postinstall hook only copies a missing KORAINIT.md into the project root.
- Claude hook installation and removal are selected by an explicit CLI verb.
- No package network endpoint or confirmed credential exfiltration was identified in the inspected source.
Source & flagged code
16 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
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 koragraphmcp@0.1.5.
See all versions of koragraphmcp for other recorded verdicts.
- Review the evidence and your use of koragraphmcp@0.1.5 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.