The Agent Skills Directory

[SAFE]: The skill implements a standard documentation retrieval client. It correctly manages sensitive information by looking for the CONTEXT7_API_KEY in environment variables or local .env files, avoiding hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it retrieves external data from the Context7 API which is then processed by the AI agent.
Ingestion points: Data is ingested through HTTP GET requests to context7.com in the _search_libs and _get_context functions in context7.py.
Boundary markers: Absent; the retrieved documentation snippets are returned to the agent without explicit delimiters or instructions to ignore embedded commands.
Capability inventory: The skill logic does not utilize eval(), exec(), or subprocess calls to process the fetched data, limiting the potential impact of any injected instructions.
Sanitization: No sanitization or filtering is performed on the retrieved text before it is passed to the agent.

context7