Notion Brain
Analysis
This is a coherent Notion-saving skill, but it can let an agent write or overwrite Notion pages and persist selected content to workspace memory without clear per-write confirmation.
Findings (4)
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.
Also trigger when an agent produces a research summary, decision memo, project plan, status update, article draft, security audit, financial snapshot, weekly rollup, contact note, meeting prep...
The skill can activate on agent-generated content, including sensitive or durable artifacts, rather than only after an explicit user request to save that specific item.
Or to fully replace content (use with care): ... "command": "replace_content" ... "new_str": "## Updated Section\n\nFresh content replaces everything."
The documented workflow includes full replacement of existing Notion page content, which is a high-impact mutation and lacks a required backup or user confirmation step.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
The connected tools are: - `notion-search` ... - `notion-create-pages` ... - `notion-update-page` ... - `notion-fetch`
The skill expects access to connected Notion tools that can read, create, and update workspace pages; this is purpose-aligned but depends on the permissions of the user's Notion integration.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Always write to workspace memory separately when the content also matters for agent continuity.
The skill adds a second persistence path outside Notion, but does not define retention, exclusions, user approval, or how sensitive saved memory should be reused later.
