@clawling/clawchat-plugin-openclaw@2026.10.9-4
OpenClaw ClawChat channel plugin
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package has no install-time execution hook, and its runtime downloads support the documented Liveware demo feature. The sample assets are hash-checked, and the inspected credential use is part of that feature’s Liveware CLI login flow.
Decision evidence
public snapshot- The manifest has no preinstall, install, or postinstall hook; its prepublishOnly script runs typechecking.
- The optional Liveware CLI is downloaded from the vendor host media.clawling.chat.
- Downloaded sample files are SHA-256 checked against the manifest before being written.
- The sample supervisor starts only when a connection store exists and the livewareSample setting is enabled.
- The package’s skill documentation describes the Liveware Sample as an auto-installed app feature.
- The sample is enabled by default and, when it starts, passes the ClawChat account token to the Liveware CLI login command.
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@2026.10.9-4.
See all versions of @clawling/clawchat-plugin-openclaw for other recorded verdicts.
- Review the evidence and your use of @clawling/clawchat-plugin-openclaw@2026.10.9-4 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.