The Agent Skills Directory

[SAFE]: The skill's content is purely instructional and follows established software engineering best practices for continuous integration and delivery. It includes specific recommendations for security scans and dependency management.
[PROMPT_INJECTION]: The skill processes project-specific data which presents a surface for indirect prompt injection. (1) Ingestion points: The skill reads source-code, test-strategy-doc, architecture-doc, and task-list as inputs. (2) Boundary markers: The instructions do not define delimiters or warnings to ignore embedded commands within these files. (3) Capability inventory: The agent is tasked with designing stages and configuring build environments based on the provided inputs. (4) Sanitization: No sanitization or validation of the input content is mentioned.

ci-cd