The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the orth CLI to perform operations in Notion, such as orth run notion /create-page and orth run notion /search. These commands facilitate programmatic interaction with the Notion API via the vendor's toolset.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to fetch and process data from external Notion sources.
Ingestion points: Untrusted data enters the agent's context through the /search and /fetch-data actions defined in SKILL.md.
Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" directives for data retrieved from Notion.
Capability inventory: The skill possesses write capabilities through the /create-page and /add-content actions in SKILL.md, which could be exploited if malicious instructions are processed.
Sanitization: No sanitization, validation, or escaping of the fetched Notion content is described before it is utilized by the agent.

notion