The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to use curl and jq to perform REST API requests to Notion. These are standard command-line tools for making network requests and processing JSON data.
[EXTERNAL_DOWNLOADS]: The skill facilitates communication with api.notion.com. Notion is a well-known productivity platform and service, and these interactions are standard for the skill's intended functionality.
[PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it is designed to read and process content from external Notion pages and databases, which could contain malicious instructions.
Ingestion points: Operations in SKILL.md such as Retrieve block children, Retrieve a Page, and Query a Database ingest external content into the agent's context.
Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the retrieved content.
Capability inventory: The skill allows for significant workspace modifications as described in SKILL.md, including updating and deleting pages, blocks, and databases.
Sanitization: No specific sanitization or validation of the retrieved text content is specified before the agent processes it.

notion-api