The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as repositories, documents, and uploaded files to inform its interview questions. This creates a surface where malicious instructions embedded in those documents could potentially influence the agent's behavior.
Ingestion points: SKILL.md instructions specify inspecting available artifacts, repositories, documents, previous messages, diagnostics, or uploaded files.
Boundary markers: The instructions do not include specific delimiters or warnings to ignore instructions embedded in the external data.
Capability inventory: The skill utilizes the AskUserQuestion tool to interact with the user; its primary function is information extraction and synthesis.
Sanitization: There is no mention of sanitization or validation of the external content before it is processed.

interview-me