The Agent Skills Directory

[SAFE]: No security threats or malicious patterns were found in the skill's instructions or templates. The skill processes external data from PRD files and web search results, which is an inherent surface for indirect prompt injection, but the potential impact is limited by the skill's specific output constraints. Ingestion points: Reads content from local PRD.md files and tool results from web_search. Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded commands in the ingested data. Capability inventory: The skill uses web_search and generates a DESIGN_SPEC.md file. Sanitization: No input validation or sanitization is performed on the ingested content before it is processed by the agent.

designer_expert