The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of the ctx7 CLI to perform its primary functions, including documentation retrieval and configuration management.
Evidence: Commands such as ctx7 library, ctx7 docs, ctx7 skills, and ctx7 setup are utilized throughout the skill's instructions.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of external software and instructions from remote sources.
Evidence: Instructions recommend installing the ctx7 CLI via npm install -g ctx7@latest or executing it via npx.
Evidence: The ctx7 skills install /owner/repo command downloads and installs additional agent skills directly from GitHub repositories.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing external data from multiple sources.
Ingestion points: Documentation content retrieved from the Context7 API, instruction files (skills) downloaded from GitHub repositories, and local project dependency files (package.json, requirements.txt, etc.) read during the ctx7 skills suggest process.
Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are specified for the ingested content.
Capability inventory: The agent can execute CLI commands, write to project configuration files (via ctx7 setup), and install new instruction sets into the agent's skills directory.
Sanitization: The documentation explicitly warns the user and agent not to include sensitive or confidential information in search queries.
[CREDENTIALS_UNSAFE]: The skill mentions the use of environment variables and CLI flags for managing authentication secrets.
Evidence: Instructions document the use of CONTEXT7_API_KEY and the --api-key flag for handling API tokens.

context7-cli