Security audit
Security checks for vulnerabilities and agentic risk
This is a small Notion API skill whose network and write behavior fits its stated purpose, though users should treat it as capable of changing live Notion workspace data.
Install only if you intend to let the agent access your Notion workspace through a Notion integration. Use a minimal-scope Notion API key, avoid pasting real tokens into chat transcripts, and review write requests carefully because this skill can create or modify Notion pages, blocks, and data sources.
The skill has network-capable behavior against the Notion API but does not declare any explicit tool scope such as allowed tools or permissions. That omission weakens policy enforcement and reviewability, making it easier for an agent to invoke external network access without clear operator awareness or least-privilege constraints.
The skill supports write operations such as createPage, updatePage, appendBlocks, and createDataSource, but its description and usage guidance do not warn that these actions can modify or create content in a live workspace. This increases the risk of accidental destructive or unauthorized changes when an agent or user treats the skill as read-only or low-risk.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
const NOTION_VERSION = "2025-09-03";
const BASE_URL = "https://api.notion.com/v1";
async function run(params = {}) {
const op = params.input?.operation;
The manifest description says the skill is for creating/reading/updating pages, querying data sources, and appending blocks. The code also supports a separate "createDataSource" operation that creates new data sources, which is not mentioned in the described scope and materially expands the write capabilities of the skill.
The skill performs outbound HTTP requests to the Notion API using a bearer token and request bodies derived from user input, including operations that read and modify remote content. There is no confirmation prompt, logging/print statement, or explanatory comment/docstring in this file disclosing that user data and credentials are being sent to an external service.
The manifest and examples reference a sensitive Notion API credential but provide no handling or privacy guidance, such as not logging the token, not embedding it in prompts, and restricting its scope. This can lead to inadvertent credential exposure through debugging, transcripts, or unsafe operational practices.
No suspicious patterns detected.