koragraphmcp@0.1.4
Local multi-repo code-graph MCP server
AI Security Review
scanned 11d ago · by lpm-firewall-aiSource inspection shows agent configuration capabilities connected to explicit commands and limited maintenance during ingest, so this warrants a warning for agent capability risk. The install hook only copies a project guidance file and does not establish an unconsented control-surface attack.
Decision evidence
public snapshot- The postinstall hook only copies KORAINIT.md into the invoking project when the file is absent.
- The package can write generated rulebook content into supported agent instruction files during practice sync.
- Ingest refreshes only agent files Koragraph already manages; it does not create new ones.
- The hooks command installs Claude session hooks when its install verb is selected.
- The lifecycle hook skips global installs and does not configure agent hooks or execute a downloaded payload.
- Claude hook installation is invoked through the hooks command’s install path, and existing settings are preserved.
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@0.1.4.
See all versions of koragraphmcp for other recorded verdicts.
- Review the evidence and your use of koragraphmcp@0.1.4 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.