The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines an interface that processes untrusted user data, which is a common surface for indirect prompt injection.
Ingestion points: The skill ingests user-provided text in the prompt field and external content via image_url and reference_image_urls in SKILL.md.
Boundary markers: No explicit boundary markers or delimiters are defined to separate user input from the rest of the API request structure.
Capability inventory: The skill is capable of making outbound network requests to api.acedata.cloud using the provided instructions.
Sanitization: No evidence of input validation or sanitization is present in the skill documentation.

grok-video