The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources, including Zotero bibliographic metadata and Markdown generated from PDF parsing, creating a surface for potential injection attacks.
Ingestion points: Data is retrieved via zotero_item (metadata/PDFs) and omnischolar_parse (parsed Markdown output and assets).
Capability inventory: The agent can execute tools like zotero_item, omnischolar_parse, and omnischolar_sync based on the context derived from ingested content.
Boundary markers: The instructions do not specify the use of explicit delimiters or 'ignore' instructions for the parsed Markdown content before processing.
Sanitization: There is no evidence of sanitization, validation, or filtering of the external document content before it is handed off to other skills for interpretation.

paper-reading