The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires installing the omniroute package from the npm registry to function.
[COMMAND_EXECUTION]: The skill operates by executing shell commands via the omniroute CLI for tunnel management tasks like creating, stopping, and inspecting tunnels.
[INDIRECT_PROMPT_INJECTION]: The tunnel logs command allows the agent to read logs which may contain untrusted data from the internet.
Ingestion points: Output from omniroute tunnel logs in SKILL.md.
Boundary markers: None identified to separate log content from agent instructions.
Capability inventory: Ability to execute shell commands to modify tunnel states.
Sanitization: No sanitization of log output is specified.

cli-tunnel