v1.0.0

Intercom GenAIgrp

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 6:23 AM.

Analysis

The skill is a coherent, opt-in message router between OpenClaw sessions, with no evidence of hidden execution, persistence, credential use, or exfiltration.

GuidanceThis appears safe for its stated purpose. Before installing, confirm you want a skill that can send explicit `!target message` requests to other OpenClaw sessions, and do not include sensitive information unless the target session is trusted and intended to receive it.

Findings (1)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

Send via `sessions_send(sessionKey=<target>, message="FROM <sender>: <content>")`.

The skill intentionally sends user-provided content to another OpenClaw session, which is an inter-agent communication channel. The same file also bounds this to explicit `!` syntax and opt-in use.

User impactA message the user provides may be delivered to another bot/session and could influence that session or reveal information included in the message.

RecommendationUse only with intended, opted-in targets; verify the target session key and avoid sending secrets unless the receiving session should see them.