The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends using npx -y skilld to perform searches. This downloads and executes the 'skilld' package from the NPM registry, which is a well-known service. This is standard behavior for Node.js-based developer tools and originates from the NPM ecosystem.
[COMMAND_EXECUTION]: The skill instructs the agent to use skilld search to retrieve documentation, bug reports, and workarounds. These commands are localized to the search tool and do not involve arbitrary command execution or privilege escalation.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by fetching content from external sources like GitHub Issues and Discussions.
Ingestion points: Data retrieved via skilld search from external repositories.
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the search output.
Capability inventory: The agent uses the retrieved data to advise on code changes, debugging, and configuration.
Sanitization: No automated sanitization of the external text is specified. However, this is a standard capability for documentation agents and the risk is assessed as minimal within the context of developer guidance.

nuxt-test-utils-skilld