The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands to search for image assets using find, extract project information from package.json, and manage telemetry logging state.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files (e.g., idea-context.md, build-context.md, and package.json) to populate the generated pitch deck, creating a vulnerability surface where malicious content in those files could influence agent behavior.
Ingestion points: Phase 1 context gathering reads local files into the agent's context.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt instructions.
Capability inventory: The skill possesses shell execution (bash) and file-writing (HTML artifact generation) capabilities.
Sanitization: No validation or sanitization of the ingested text is performed before it is used to build the deck.
[EXTERNAL_DOWNLOADS]: The skill uses curl to transmit telemetry events to a remote URL defined in the user's local configuration file. This operation is transparently described and includes a user consent prompt.

create-pitch-deck