The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. Ingestion points: The agent ingests untrusted data when reading or editing .py files and user-defined UI specifications. Boundary markers: The skill does not instruct the agent to use markers or delimiters for the ingested data. Capability inventory: The skill employs reflex init for template-based initialization and uv run for code validation. Sanitization: No sanitization or filtering of external code content is defined in the workflow.

reflex-usage