The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as metrics, survey results, and reports to generate video scripts and narration.
Ingestion points: The 'Inputs' section specifies that the skill takes data from reports, notes, and pasted metrics or ROI figures.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the provided data.
Capability inventory: The skill has the ability to generate video content, narration, and public review/export links using the clueso-mcp tool.
Sanitization: The instructions do not mention any sanitization, validation, or filtering of the input data.
[COMMAND_EXECUTION]: The skill instructs the agent to offer and potentially execute shell commands to set up the Clueso tool connection.
Evidence: Instruction to run claude mcp add --transport http Clueso https://connect.clueso.io/mcp for setup on certain platforms.
[EXTERNAL_DOWNLOADS]: The skill references and directs the agent to connect to an external service and documentation site belonging to the developer.
Evidence: Use of https://connect.clueso.io/mcp for tool connection and https://help.clueso.io/mcp-setup for setup documentation.

stats-infographic-video