The Agent Skills Directory

[SAFE]: The skill is entirely composed of text-based instructions for architectural modeling and domain decomposition. It does not include any executable code, scripts, or external dependencies.- [PROMPT_INJECTION]: No attempts to bypass safety filters, override system instructions, or extract system prompts were found. The instructional language is standard for a design advisor.- [DATA_EXFILTRATION]: There are no network requests, API calls, or commands that access sensitive files such as environment variables or credentials.- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level operations are defined or requested within the skill files.- [INDIRECT_PROMPT_INJECTION]: * Ingestion points: The skill gathers business goals, user journeys, and technical constraints as external input in the 'Inputs To Gather' section of SKILL.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the input data are provided. * Capability inventory: The skill has no access to tools, scripts, or file-writing capabilities. * Sanitization: No sanitization or validation of the input data is performed. * Evaluation: While the skill lacks input boundaries, the absence of any exploitable capabilities (such as code execution or network access) ensures there is no functional risk from indirect injection.

domain-decomposition-api-design-advisor