The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of transforming user-provided specifications into executable code structures.
Ingestion points: The $ARGUMENTS variable in SKILL.md serves as the entry point for external data describing component requirements.
Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" directives to prevent the agent from obeying commands hidden within the component specifications.
Capability inventory: The skill utilizes the agent's ability to generate multiple source files (components, tests, styles). A successful injection could influence the content of these generated files.
Sanitization: There is no defined process for validating or escaping the input provided in $ARGUMENTS before it is interpolated into the code generation logic.
[SAFE]: The automated alert for FileRepMalware is identified as a false positive. The skill's content is composed entirely of standard React development templates, TypeScript interfaces, and testing patterns (Jest, React Testing Library). No exfiltration, obfuscation, or persistence mechanisms were detected after manual review.

frontend-mobile-development-component-scaffold