The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted external data.
Ingestion points: The skill utilizes MCP tools extract_text_from_pdf and read_xlsx to ingest data from external files (invoices, receipts, spreadsheets).
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted content from system instructions or to warn the agent about potential embedded commands in the processed files.
Capability inventory: The skill possesses the capability to write to the file system using the create_xlsx tool.
Sanitization: No sanitization or validation logic is specified for the content extracted from external files before it is processed by the agent.

Invoice Organizer