The Agent Skills Directory

[PROMPT_INJECTION]: The instructions include a 'CRITICAL: Auto-start on load' directive. This uses high-priority keywords to override standard agent behavior and force the model into a specific workflow immediately upon activation.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, making it vulnerable to instructions hidden within the uploaded files.
Ingestion points: User-uploaded .xlsx files, specifically sheets named 'DISCOVERY', 'ENGAGEMENT', 'TOP POSTS', 'FOLLOWERS', and 'DEMOGRAPHICS'.
Boundary markers: Absent; there are no instructions provided to the agent to treat spreadsheet cell content strictly as data or to ignore any natural language instructions found within them.
Capability inventory: The skill reads data to generate a React-based dashboard (code generation) and provides a detailed strategic written analysis.
Sanitization: Absent; the instructions do not require the agent to sanitize, escape, or validate the content of the spreadsheet before processing it.
[DYNAMIC_EXECUTION]: The skill requires the agent to generate a functional React artifact (using the Recharts library) at runtime based on the processed external data, which is a form of dynamic code generation.

analytics-dashboard