The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes programmatic HTTP requests using fetch and provides curl examples to interact with the frontpage.sh API for pricing and purchasing grid pixels.
[DATA_EXFILTRATION]: User-provided email addresses are sent to the vendor's servers to facilitate purchase receipts and newsletter enrollment, which is a disclosed and core part of the service's functionality.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads user-generated content (labels and URLs) from the public grid.
Ingestion points: Data is ingested through the GET /api/million/grid endpoint as described in SKILL.md.
Boundary markers: The instructions do not specify explicit boundary markers or delimiters for the ingested content.
Capability inventory: The skill can perform network operations via fetch and authorize financial transactions using the platform's MPP (Machine-to-Machine Payment) SDK.
Sanitization: The service utilizes server-side moderation to filter content, though the skill itself does not specify client-side sanitization of the retrieved grid data.

frontpage-million