The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script from the author's GitHub repository using bash -c "$(curl -fsSL ...)". This method executes remote code directly in the user's shell environment.
[REMOTE_CODE_EXECUTION]: The skill uses cargo install --git to pull and build remote code from the author's repository.
[EXTERNAL_DOWNLOADS]: The skill downloads various components from external GitHub repositories under the author's namespace (yjmeqt), including the Remo SDK via Swift Package Manager and CocoaPods, and the CLI via a Homebrew tap.
[COMMAND_EXECUTION]: The skill utilizes several shell commands to verify the environment and orchestrate the remo CLI tool for device discovery and application inspection.
[PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes untrusted output from external applications via the Remo CLI.
Ingestion points: Commands such as remo devices, remo tree, remo info, and remo call (in references/cli.md) ingest data from running simulators or devices into the agent's context.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat application data as untrusted or separate from instructions.
Capability inventory: The agent has the ability to execute shell commands, interact with the local file system (saving screenshots and videos), and perform CLI-based orchestration.
Sanitization: The instructions do not include any steps for sanitizing, validating, or filtering the data received from the Remo-enabled applications before processing.

remo-setup