@clawling/clawchat-plugin-openclaw@2026.10.21-1
OpenClaw ClawChat channel plugin
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe plugin automatically reports installation and runtime details to its own service during startup, with no disclosure or opt-out found in the inspected package. The fields are limited and no secret exfiltration was identified, so this is suspicious telemetry rather than a block-level attack.
Static reason
No blocking static signals were detected.
Trigger
Automatic when the plugin runtime starts, and again after account activation.
Impact
Allows the service to associate installations with software versions and reported capability facts. No credential theft or unrelated data collection was identified.
Mechanism
Sends a device ID, platform and plugin/runtime versions, with optional onboarding capability facts, to the configured API base URL; the paired report uses the account token.
AI rationale
The plugin automatically reports installation and runtime details to its own service during startup, with no disclosure or opt-out found in the inspected package. The fields are limited and no secret exfiltration was identified, so this is suspicious telemetry rather than a block-level attack.
Evidence
src/runtime.tssrc/plugin-report.tssrc/api-client.tssrc/config.ts
Network endpoints2
app.clawling.com — /v1/agents/plugin-reportapp.clawling.com — /v1/agents/me/plugin-report
Decision evidence
public snapshotAI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- Runtime startup automatically sends a plugin report to the account’s configured API base URL, initially without authentication.
- The report includes a device ID, platform and plugin/runtime versions, plus optional onboarding report fields.
- After activation, the plugin sends a paired report with the ClawChat account token to its authenticated API endpoint.
- The manifest declares no install, preinstall or postinstall hook.
- The package describes its default API host as app.clawling.com.
Evidence against
- The report contains version and runtime data and limited onboarding fields; the inspected code does not show it collecting credentials or unrelated files.
- The authenticated report uses the account token with the ClawChat API, consistent with the package’s service.
- The manifest’s scripts are build, pack, publish, release and development commands rather than install hooks.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystem
Source & flagged code
4 flaggeddist/src/plugin-report.jsView file
17try {
L18: const require = createRequire(import.meta.url);
L19: let dir = dirname(fileURLToPath(import.meta.url));
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/src/plugin-report.jsView on unpkg · L17dist/src/dm-recall-default.js#virtual:normalized:round1View file
•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 4
High
Semantic Analysis Limited
A 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 unpkgpackage.json
Findings
1 Critical1 High5 Medium5 Low
CriticalManifest Confusionpackage.json
HighSemantic Analysis Limiteddist/src/dm-recall-default.js#virtual:normalized:round1
MediumDynamic Requiredist/src/plugin-report.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
MediumAi Review Evidencesrc/runtime.ts
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @clawling/clawchat-plugin-openclaw@2026.10.21-1.
See all versions of @clawling/clawchat-plugin-openclaw for other recorded verdicts.
- Review the evidence and your use of @clawling/clawchat-plugin-openclaw@2026.10.21-1 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.