The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the ctx7 package globally using NPM (npm install -g ctx7@latest) or to run it directly using npx. This involves downloading and executing code from the public NPM registry.
[COMMAND_EXECUTION]: The skill's primary functionality relies on executing shell commands, specifically ctx7 library and ctx7 docs, to resolve library IDs and retrieve documentation content.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes technical documentation from external, third-party sources.
Ingestion points: The output of the ctx7 docs <libraryId> <query> command, which returns code snippets and prose descriptions from indexed documentation (SKILL.md).
Boundary markers: None identified; there are no specific delimiters or instructions for the agent to ignore embedded commands within the retrieved documentation.
Capability inventory: The agent can execute shell commands via the ctx7 CLI and potentially other tools available in the environment.
Sanitization: The skill includes instructions for the agent to avoid including sensitive data in its queries, but it does not specify any sanitization or filtering for the content returned by the CLI before it is processed by the agent.
[DATA_EXFILTRATION]: Technical queries are sent to the Context7 API. The skill explicitly warns against including sensitive or confidential information like API keys, passwords, or proprietary code in these queries, which is a positive security practice.

context7