The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides an installation command curl -fsSL https://ntn.dev | bash which downloads a script from an external domain and executes it directly in the shell. This pattern allows for arbitrary code execution on the host system from a source that is not verified as a well-known service or trusted organization.\n- [COMMAND_EXECUTION]: The skill's instructions involve executing various ntn commands with parameters derived from user or external input, such as page IDs, file paths, and JSON bodies. This creates a surface for command injection if inputs are maliciously crafted or improperly handled by the agent.\n- [DATA_EXFILTRATION]: The skill enables reading local files (e.g., ntn files create < image.png) and uploading data to the Notion API. These capabilities can be leveraged to exfiltrate sensitive local data to an external service without explicit user consent.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its data ingestion features.\n
Ingestion points: The ntn pages get and ntn api commands retrieve content from external Notion databases and pages.\n
Boundary markers: The skill does not provide any delimiters or instructions to the agent to treat retrieved content as untrusted data.\n
Capability inventory: The skill has the ability to execute shell commands, read local files, and transmit data over the network.\n
Sanitization: There is no evidence of sanitization or validation of the content retrieved from the Notion API.\n- [DECEPTIVE_METADATA]: The skill's LICENSE.md file contains a copyright notice for "Notion Labs, Inc." with the year "2026". This misleadingly suggests official affiliation with the Notion company and provides false metadata regarding the skill's origin and maturity.

notion-cli