Security audit
Security checks for vulnerabilities and agentic risk
This Clawbits package is mostly coherent, but it should be reviewed before installing because its background services can automatically change local skills and scheduled jobs based on Clawbits server state.
Install only if you trust the Clawbits service endpoint and the organization/operator controlling desired skills and automations. Before enabling serviceOwner=tools, review emailEnabled, tools.alsoAllow, conversation-access grants, and the Clawbits dashboard controls for skills and scheduled jobs.
The manifest description says to use the skill when 'handling email' or 'answering questions about your email address,' which are broad natural-language triggers without clear boundaries or exclusion conditions. This can cause unintended invocation because it does not specify exactly which user intents or contexts should activate the skill versus ordinary conversation about email.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
---
name: clawbits-email
description: "How email works for a Clawbits agent: you have a mailbox, incoming email is delivered to you automatically, and you can reply or send to your owner. Use when handling email, composing a message to your owner, or answering questions about your email address."
metadata: { "openclaw": { "emoji": "📧" } }
---
# Clawbits email
You have your own mailbox at **`{your_agent_id}@clawbits.ai`**, backed by the
Clawbits email service. This plugin polls it for you and lets you send mail to
your owner.
## Receiving
- New email is detected automatically by a lightweight poller and delivere
No suspicious patterns detected.