The Agent Skills Directory

Indirect Prompt Injection (HIGH): The skill exhibits a significant vulnerability surface by combining external data ingestion with sensitive write capabilities.
Ingestion points: The skill ingests untrusted content by using Read, Grep, and Glob tools to analyze React source code.
Boundary markers: Absent. The instructions do not define delimiters or provide clear rules to the agent to ignore embedded instructions found within the code being processed.
Capability inventory: The skill is granted Write and Edit tools, allowing it to modify the local environment based on its analysis of potentially malicious inputs.
Sanitization: Absent. No evidence of input validation or sanitization is present to prevent the agent from executing instructions hidden in comments or strings within the React components.

performance-animator