The Agent Skills Directory

[SAFE]: The skill follows established UI development patterns and restricts its operations to standard filesystem tools (Read, Write, Edit, Grep, Glob) within the project context. It does not perform network operations or attempt to access sensitive system files.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from user-specified files and local configuration files to generate component code, which constitutes a standard attack surface for indirect prompt injection.
Ingestion points: Reads the target file path provided in arguments, as well as local files like DESIGN-LANGUAGE.md and registry files in the .styleseed/ directory.
Boundary markers: None detected in the instructions.
Capability inventory: The skill uses Read, Write, Edit, Grep, and Glob tools to modify project source code.
Sanitization: No specific sanitization or validation of the ingested content is performed before interpolation into the generated UI code.
Conclusion: The risk is minimal as the skill relies on rigid TSX templates and specific UI rules for the output generation, which is consistent with legitimate developer assistant behavior.

ss-feedback