@clawling/clawchat-plugin-openclaw@2026.10.11-3
OpenClaw ClawChat channel plugin
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package performs undisclosed runtime reporting and defaults to starting a downloaded sample app when the account has no Liveware apps. These behaviors merit a warning; the reporting stays with the configured service and the sample is sourced from the vendor’s official repository with file hash checks.
Decision evidence
public snapshot- Gateway startup sends a plugin report before credentials are available, then sends another after activation.
- The report includes a stable hashed device ID and plugin, host, and Node versions.
- The Liveware Sample feature defaults to enabled and its supervisor starts automatically with the gateway.
- When the account has no Liveware apps, the supervisor downloads the sample, runs its server with Node, and registers it with ClawChat.
- The reports go to the account’s configured ClawChat service and contain version fields plus a hashed device ID, not raw credentials.
- The sample is fetched from the vendor’s official repository and each downloaded file is checked against a manifest SHA-256.
- The manifest has no preinstall, install, or postinstall script; its lifecycle script is prepublishOnly.
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/dm-recall-default.js#virtual:normalized:round1View on unpkgFindings
Affected versions and remediation
This report applies to @clawling/clawchat-plugin-openclaw@2026.10.11-3.
See all versions of @clawling/clawchat-plugin-openclaw for other recorded verdicts.
- Review the evidence and your use of @clawling/clawchat-plugin-openclaw@2026.10.11-3 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.