The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions specify the use of npx -y modern-web-guidance@latest to fetch code from the NPM registry. The package is associated with a well-known service (Google).
[COMMAND_EXECUTION]: The skill requires the execution of shell commands to interact with the guidance tool. This involves running external code in the user's environment to search and retrieve data.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process data from external sources.
Ingestion points: Untrusted data enters the agent's context through the output of the modern-web-guidance retrieve command, which fetches markdown content from a remote source.
Boundary markers: The instructions do not define any specific delimiters or instructions for the agent to distinguish between the skill's own logic and the content of the retrieved guides.
Capability inventory: The skill primarily performs searches and reads data, but the content it retrieves could theoretically influence the behavior of an agent possessing broader capabilities such as file system access or network operations.
Sanitization: There is no mention of validation or filtering of the retrieved content before it is processed by the agent's language model.

modern-web-guidance