The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as user research, validated evidence, and product scope requirements. While this creates a potential surface for indirect prompt injection, the risk is minimal as the skill does not perform high-risk actions (like code execution or network requests) and explicitly instructs the agent to use synthetic fixtures and maintain traceability to authorized evidence. Evidence of mitigation includes instructions in references/usability-testing-and-privacy.md to use synthetic data and authorized observations only.

product-design-and-ux