The Agent Skills Directory

[SAFE]: The skill instructions define a standard UI verification process using established developer tools and platform MCPs. No malicious patterns, data exfiltration, or unauthorized command execution were identified.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data, creating a potential surface for indirect instructions, though the risk is minimal given the specific UI verification context.
Ingestion points: Figma design data via the get_design_context MCP tool and reference screenshots provided by the user in SKILL.md.
Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present in the skill definition.
Capability inventory: The skill uses git branch --show-current and interacts with Mobile/Dart MCPs for screenshot capturing and deployment.
Sanitization: No explicit sanitization or content validation steps are implemented for the ingested design data.

verify-ui