skills/makenotion/skills/notion-cli/Gen Agent Trust Hub

notion-cli

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill contains an installation command curl -fsSL https://ntn.dev | bash which pipes a remote script directly to the shell. This is the official installation method for the Notion CLI tool provided by the vendor.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute various ntn commands to query databases, manage pages, deploy workers, and interact with the Notion API.
  • [EXTERNAL_DOWNLOADS]: Fetches the ntn CLI tool from https://ntn.dev and supports uploading files to Notion or fetching external URLs via ntn files create.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves external data (Notion pages) that could contain malicious instructions.
  • Ingestion points: Page content is retrieved into the agent's context using the ntn pages get <page-id> command in SKILL.md.
  • Boundary markers: No boundary markers or ignore-instruction warnings are specified to isolate external page content from the system prompt.
  • Capability inventory: The skill has access to shell execution for CLI commands and API operations across SKILL.md.
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from Notion before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 09:59 AM