The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @youmind-ai/cli package from the NPM registry. This is the official command-line tool for the YouMind service which provides the underlying infrastructure for the skill's features.\n- [COMMAND_EXECUTION]: Shell commands are used to invoke the youmind CLI for interacting with the service API. The workflow instructs the agent to interpolate user-provided descriptions into CLI arguments, which could present a command injection surface if the agent platform does not properly escape the input during execution.\n- [DYNAMIC_EXECUTION]: The skill uses node -e to execute a JavaScript snippet that parses JSON data retrieved from the API. The script is hardcoded in the skill instructions and used for data extraction and processing of the remote API response.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from the YouMind API (generated webpage results). This introduces a potential surface for indirect prompt injection if the remote content contains malicious instructions designed to influence the agent's behavior during subsequent steps.\n
Ingestion points: Content retrieved via youmind call listMessages and processed by the node -e script in SKILL.md.\n
Boundary markers: None explicitly defined in the processing instructions to separate user data from instructions.\n
Capability inventory: Network access (via CLI), shell execution, and user-facing output links to the YouMind platform.\n
Sanitization: The skill extracts data from JSON fields but does not perform specific sanitization or escaping on the text content within those fields before returning it to the user or agent.

youmind-webpage-generator