The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-provided content through the $ARGUMENTS parameter and interpolates it directly into the Notion ticket's name, properties, and body.
Ingestion points: The $ARGUMENTS input field in SKILL.md is the primary source of untrusted data.
Boundary markers: The instructions do not define clear delimiters or use unique tags to separate the user-provided data from the agent's internal logic, which could allow a malicious user to include instructions that influence the ticket creation process.
Capability inventory: The skill uses the Notion MCP create-page tool, which allows writing data to a remote Notion database (9bde6985-9747-4684-b969-c8ecec481b63).
Sanitization: There is no mention of sanitizing or escaping the user's input before it is used to populate ticket fields or the markdown body template.

create-ticket