The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the omniroute command-line utility to perform administrative tasks such as creating, rotating, revealing, and revoking API keys.\n- [EXTERNAL_DOWNLOADS]: The skill requires the agent to install the omniroute package globally from the npm registry using npm install -g omniroute.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes subcommands that process external input as shell arguments, creating an attack surface for indirect prompt injection.\n
Ingestion points: Arguments in subcommands like keys add <provider> [apiKey], keys reveal <id>, and oauth status --provider <id> are derived from external data.\n
Boundary markers: The instructions do not define delimiters or specific warnings to prevent the agent from misinterpreting instructions embedded within these inputs.\n
Capability inventory: The agent has the capability to execute shell commands and reveal sensitive API keys via the omniroute binary.\n
Sanitization: No explicit sanitization or validation logic is provided to handle potentially malicious input before it is interpolated into shell commands.

cli-keys