The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on a Python script (scripts/cliproxyapi_manager.py) and platform-specific shell wrappers (.sh, .ps1, .bat) to execute management commands and interact with the CLIProxyAPI service.
[DATA_EXFILTRATION]: The skill is designed to transmit sensitive management keys and authentication files (such as service account JSON tokens) to a user-configured API endpoint. This behavior is the primary intended function of the skill for remote management.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from the CLIProxyAPI Management API, which serves as a potential attack surface for indirect prompt injection.
Ingestion points: API response bodies are ingested and parsed within the http_request and decode_body functions in scripts/cliproxyapi_manager.py.
Boundary markers: The skill does not employ specific delimiters or instructions to ignore embedded commands when displaying API output to the agent.
Capability inventory: The skill possesses capabilities for network communication (via urllib), file system writes (via the --output parameter), and management of local configuration files.
Sanitization: The script includes a redact function that automatically masks values associated with sensitive keys (e.g., api-key, secret, token, bearer) before printing JSON output to the console.

cliproxyapi-manager-skill