The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell and Node.js scripts (scripts/search, scripts/search.mjs) to interact with the Valyu API and manage its configuration.
[DATA_EXFILTRATION]: The skill transmits search queries and a user-provided API key to the Valyu service at https://api.valyu.ai to retrieve search results.
[PROMPT_INJECTION]: The skill processes full-text content from external research papers, which constitutes an indirect prompt injection attack surface.
Ingestion points: The content field returned by search queries, which contains the full text of bioRxiv preprints.
Boundary markers: None identified in the skill's instructions to delineate retrieved content from system instructions.
Capability inventory: The skill environment can execute shell commands through the provided search scripts.
Sanitization: The documentation does not mention sanitization or validation of the text content retrieved from the external database.

biorxiv-search