The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as user research notes and feature requests, which could contain hidden instructions. Ingestion points: Processes user research interview notes, survey results, and feature requests as defined in the Inputs section of SKILL.md. Boundary markers: The instructions do not prescribe the use of delimiters or specific warnings to ignore instructions embedded within the processed research content. Capability inventory: The skill description indicates it is integrated with the codebase and can reference APIs and technical constraints (SKILL.md). Sanitization: The skill does not define methods for sanitizing or validating the content of the external data before processing.

product-management