The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the agent to fetch platform documentation from official URLs such as https://render.com/docs/compute-plans.md and https://render.com/docs/private-network.md. These downloads target the well-known service provider's domain to ensure the agent uses current specifications for plan IDs and networking constraints.
[INDIRECT_PROMPT_INJECTION]: The skill includes a documentation-retrieval workflow where the agent processes content from external URLs. While this introduces an ingestion surface for potentially untrusted data, the instructions restrict retrieval to the provider's official domain and specify that the agent should only use the content to verify stable constraints.
[CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill follows security best practices by using environment variables (e.g., REDIS_URL) and clear placeholders (e.g., YOUR_PASSWORD) in its connection examples.

render-keyvalue