The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided data in multiple formats, creating a surface for indirect instructions to be passed to the agent.
Ingestion points: The instructions.md file explicitly directs the agent to accept and process data from CSV, Excel, and JSON files.
Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores natural language instructions that might be embedded within the data rows of processed files.
Capability inventory: The skill possesses filesystem write capabilities through the export_to_excel method in SKILL.md and maintains internal state for warranties and documents.
Sanitization: The skill lacks validation or sanitization logic to verify that the content of the processed files matches the expected schema and does not contain adversarial instructions.

warranty-tracker