The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill's installation instructions include the command curl -fsSL https://ntn.dev | bash. This pattern downloads a script from a remote domain and pipes it directly into the shell for execution, which is a high-risk practice that can be exploited for supply chain attacks if the remote server or domain is compromised.
[COMMAND_EXECUTION]: The skill is designed to execute various subcommands of the ntn binary, including those that interact with the network (ntn api), manage files (ntn files), and deploy code (ntn workers deploy).
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external source, creating a vulnerability surface for indirect prompt injection.
Ingestion points: The ntn pages get <page-id> command retrieves Markdown content from Notion pages and presents it to the agent (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or clear "ignore embedded instructions" warnings when processing page content.
Capability inventory: The skill possesses significant capabilities, including arbitrary API calls via ntn api, file uploads via ntn files create, and code deployment via ntn workers deploy (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Notion before it is processed by the agent.
[CREDENTIALS_UNSAFE]: The skill relies on and instructs the user regarding the management of the NOTION_API_TOKEN. While this is functional, it involves the handling of high-privilege secrets that grant access to the user's workspace.

notion-cli