@clawling/clawchat-plugin-openclaw@2026.10.8-2
OpenClaw ClawChat channel plugin
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package automatically deploys and publicly tunnels a publisher-selected demo app when the account has no Liveware apps, using the account token without a separate deployment request. The sample download is hash-checked and the reviewed source shows no unrelated credential exfiltration, so this warrants a warning rather than a malicious verdict.
Decision evidence
public snapshot- The Liveware Sample setting defaults to true when unset.
- Gateway runtime starts the sample supervisor automatically for an account with a store.
- If the account has no Liveware apps, startup downloads the sample and launches its server.
- The supervisor logs in with the ClawChat token, creates a Liveware app, starts a public tunnel and registers the app without an explicit user request.
- Sample files are checked against SHA-256 values in the fetched manifest.
- The sample is skipped when the account already has a Liveware app.
- The reviewed flow shows no unrelated credential collection or transmission.
Source & flagged code
4 flaggedPackage source references dynamic require/import behavior.
dist/src/plugin-report.jsView on unpkg · L17A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/src/storage.js#virtual:normalized:round1View on unpkgFindings
Affected versions and remediation
This report applies to @clawling/clawchat-plugin-openclaw@2026.10.8-2.
See all versions of @clawling/clawchat-plugin-openclaw for other recorded verdicts.
- Review the evidence and your use of @clawling/clawchat-plugin-openclaw@2026.10.8-2 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.