memory-to-notion
Analysis
The skill is coherent for saving memories to Notion, but it can broadly scan past conversations and persist selected personal details in a Notion workspace with limited scoping and approval details.
Findings (3)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
OpenClaw accesses Notion through a separately installed "notion" skill ([clawhub.ai/steipete/notion](https://clawhub.ai/steipete/notion)). This skill must be installed before using memory-to-notion. When executing, first read the notion skill's SKILL.md
The workflow depends on another skill and its instructions, but that dependency is not included in the provided artifacts.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
All operations described in this skill (search, query, create page, update page, create database) map directly to the notion skill's REST API patterns
The skill needs Notion account authority that can search the workspace and create or update Notion content; this is purpose-aligned but sensitive.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
This skill retrieves the user's past conversation history, analyzes it for valuable and meaningful content, decomposes conversations into atomic memory entries, and writes them as rows into the Memory Store Notion Database.
This shows broad access to private conversation history and persistent export of selected memory content into an external Notion database.
