The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses pnpx ctx7@latest to download the ctx7 package from the npm registry. This occurs at runtime to ensure the latest version of the CLI tool is used.- [REMOTE_CODE_EXECUTION]: By using pnpx, the skill downloads and immediately executes code from a remote repository (npm). The ctx7 commands are invoked with arguments derived from user input.- [COMMAND_EXECUTION]: The skill relies on executing shell commands (ctx7 library, ctx7 docs, ctx7 login) to perform its core functions. It also uses export to set environment variables for API key management.- [DATA_EXFILTRATION]: User-provided documentation queries are sent to the Context7 backend API. The skill explicitly warns against including sensitive data like API keys, passwords, or credentials in these queries to mitigate privacy risks.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external documentation and code snippets.
Ingestion points: Output from ctx7 library and ctx7 docs (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from obeying instructions found within the retrieved documentation.
Capability inventory: Execution of shell commands via the ctx7 CLI tool.
Sanitization: The skill includes instructions to avoid passing sensitive information into the queries, but lacks sanitization for the data returned by the tool.

find-docs