The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion and processing of external data sources, which presents a surface for indirect prompt injection attacks.
Ingestion points: Data enters the agent context through tools such as process_attached_csv and submit_bulk_job using parameters like fileUrl, csv, or rows as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or clear separation markers to distinguish data from instructions during processing.
Capability inventory: The skill has the capability to perform network requests to the api.leadmagic.io domain.
Sanitization: There is no evidence of content sanitization, filtering, or validation for the data ingested from external files or URLs.

bulk-jobs