The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using bunx to interact with the Context7 CLI (e.g., bunx ctx7 library and bunx ctx7 docs). This is the intended core functionality of the skill for searching and fetching documentation.- [EXTERNAL_DOWNLOADS]: The skill uses bunx to dynamically download and execute the ctx7 package from the npm registry. This is a standard method for utilizing Node.js-based utilities without permanent installation.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes content from an external source (the Context7 documentation service). • Ingestion points: Untrusted data enters the agent context through the output of the bunx ctx7 docs command. • Boundary markers: No explicit markers or instructions are provided to the agent to treat the fetched documentation as data rather than instructions. • Capability inventory: The skill facilitates command execution via bunx across its scripts. • Sanitization: There is no evidence of content filtering or sanitization of the retrieved documentation before it is processed by the agent.

context7