The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a mandatory workflow that relies on ingesting and processing data from external sources, creating a potential surface for indirect prompt injection.
Ingestion points: The SKILL.md file mandates a workflow that includes fuse-ai-pilot:explore-codebase for analyzing the current project's code and mcp__context7__query-docs for querying external Laravel documentation.
Boundary markers: There are no explicit instructions or delimiters provided in the workflow to warn the agent against executing instructions that might be embedded within the codebase or documentation being analyzed.
Capability inventory: The skill is designed to generate API controllers, resources, and authentication logic, which involves writing executable PHP code to the local filesystem.
Sanitization: The skill does not specify any sanitization or validation protocols for the information gathered during the research phase before it is interpolated into the agent's code generation process.

laravel-api