The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs users to install and run code using npx -y easy-notion-mcp or by cloning https://github.com/Grey-Iris/easy-notion-mcp.git followed by npm install and npm run build. These methods involve downloading and executing code from external, untrusted third-party sources.
[EXTERNAL_DOWNLOADS]: The skill documentation points to external code hosted on the NPM registry (easy-notion-mcp) and a GitHub repository (Grey-Iris/easy-notion-mcp) for deployment.
[COMMAND_EXECUTION]: Setup involves executing local shell commands such as git clone, npm install, and npm run build, which are triggered by the user following the skill's instructions.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Notion pages and databases, which could contain malicious prompts designed to hijack the agent's behavior.
Ingestion points: Data enters the agent's context through read_page, query_database, and search_notion tools.
Boundary markers: The skill provides a NOTION_TRUST_CONTENT configuration (defaulting to false) which adds a content-notice prefix to ingested data as a safety measure.
Capability inventory: The skill possesses extensive capabilities, including creating, updating, and deleting Notion content, as well as uploading files from the local filesystem.
Sanitization: Documentation mentions the use of content sanitization and URL validation to mitigate risks.

easy-notion-mcp-integration