Security audit
Security checks for vulnerabilities and agentic risk
This is a local personal-assistant skill that saves user-entered reminders, notes, contacts, and similar data on the machine, with no artifact evidence of hidden network use or destructive behavior.
Install only if you are comfortable with the skill keeping local records of reminders, notes, contacts, expenses, habits, links, and usage history under ~/.openclaw/smart-daily-assistant/. Use explicit commands when possible, and periodically review or delete that local folder if you no longer want the saved data.
The description claims activation for "any daily personal assistant task," which is overly broad and can cause the skill to trigger on ordinary conversation unrelated to explicit user intent. In an assistant that can read and write local files, unintended activation increases the chance of accidental persistence of personal data or unwanted state changes.
The skill creates persistent storage under ~/.openclaw and automatically saves reminders, notes, contacts, and other personal data across sessions. Session persistence is risky here because the stored content is sensitive personal information, and automatic persistence on first message can retain data longer than the user expects.
On first message, create data directory:
mkdir -p ~/.openclaw/smart-daily-assistant
Broad triggers like "good morning" and "briefing" are common conversational phrases and may activate the skill without the user intending to invoke it. Because the skill persists data and may expose summaries of stored reminders or notes, accidental invocation can create privacy and integrity risks.
Using "help" as a standalone trigger is too generic and likely to collide with normal assistant usage, causing unintended skill activation. In this skill, accidental activation is more concerning because it can lead to reading, writing, or disclosing locally stored personal information in response to an otherwise general request for help.
The initial settings specify 'language': 'english', which imposes a language preference by default. The policy requires offering language choice or obtaining user opt-in unless the locale constraint is clearly justified.
No suspicious patterns detected.