The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the omniroute package from the public npm registry using npm install -g omniroute. This is a standard procedure for using the vendor's CLI tool.
[COMMAND_EXECUTION]: The skill provides a comprehensive set of instructions for executing the omniroute CLI utility. It covers subcommands for auditing (audit tail, search, export), policy management (policy list, create, evaluate), and telemetry monitoring.
[INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface where untrusted data could be introduced into the agent's context through CLI outputs.
Ingestion points: The subcommands audit search <query>, policy evaluate --context <json>, and policy import <file> in SKILL.md ingest external data.
Boundary markers: The skill does not define specific delimiters to separate tool output from agent instructions.
Capability inventory: The skill can execute shell commands and write data to the local file system using the --export and --out flags.
Sanitization: No explicit sanitization or validation of the CLI output is described in the skill instructions.

cli-policy-audit