The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides a command to download and execute an installation script directly from the vendor's GitHub repository (https://raw.githubusercontent.com/render-oss/cli/refs/heads/main/bin/install.sh | sh). This is the official installation method for the tool.
[COMMAND_EXECUTION]: The CI/CD example uses sudo to move the downloaded CLI binary to /usr/local/bin. This is a routine operation for software installation in automated environments.
[DATA_EXPOSURE]: The skill references the configuration file ~/.render/cli.yaml, which stores authentication tokens. This is the standard local storage path for the tool's credentials.
[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read external data that could contain malicious instructions.
Ingestion points: Commands like render logs and render psql ingest potentially untrusted data from service logs and database queries into the agent's context.
Boundary markers: The provided instructions do not include specific delimiters or warnings to ignore instructions found within logs or database output.
Capability inventory: The agent can execute shell commands, manage services, and access databases via the render CLI.
Sanitization: There is no evidence of sanitization for the data retrieved from logs or database queries before it is processed by the agent.

render-cli