The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install an external binary using go install github.com/lox/notion-cli@latest. This downloads and compiles code from the author's public GitHub repository at runtime.
[COMMAND_EXECUTION]: The skill relies on executing the notion-cli command via the Bash tool to perform operations such as searching, viewing, creating, and editing Notion content. This includes commands that interact with the local file system, such as notion-cli page upload ./document.md.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external source (Notion).
Ingestion points: Untrusted data enters the agent context through notion-cli page view, notion-cli search, notion-cli db query, and notion-cli comment list in SKILL.md.
Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between its system instructions and the content retrieved from Notion.
Capability inventory: The skill possesses the capability to modify or delete data (archive, edit, create) within the Notion workspace using notion-cli.
Sanitization: No sanitization or filtering is applied to the content fetched from Notion before it is processed by the agent.

notion