The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, making it susceptible to indirect prompt injection if the inputs contain adversarial instructions.
Ingestion points: The skill processes user-submitted astronomical manuscripts and external data retrieved from Springer Nature/Nature Astronomy websites during the "Official-submission checklist" phase.
Boundary markers: The skill does not provide specific delimiters or instructions to the agent to treat external manuscript text as data rather than instructions.
Capability inventory: The skill requires file-read access (to ../../resources/source-basis.md and ../../resources/official-source-map.md) and network access via search tools to verify live journal policies.
Sanitization: There are no explicit instructions for the agent to sanitize, filter, or validate the content of the manuscripts or web data before processing.

nature-astronomy