The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses environment variables ($F5_MCP_SCRIPT, $MCP_CALL) to define the path of the execution script and the command-line caller, enabling dynamic execution of F5 management tools.- [CREDENTIALS_UNSAFE]: The provided command examples pass the $F5_AUTH_STRING environment variable directly on the command line, potentially exposing authentication tokens in process listings or shell history files.- [PROMPT_INJECTION]: The skill includes tools that read system logs and object configurations from the F5 device, creating a surface for indirect prompt injection. 1. Ingestion points: System logs (show_logs_tool) and virtual server/pool configurations (list_tool). 2. Boundary markers: None. No instructions are provided to the agent to treat log data as untrusted or to ignore embedded instructions. 3. Capability inventory: The skill has high-impact capabilities including update_tool, create_tool, and delete_tool, which can modify network configuration. 4. Sanitization: No sanitization of the retrieved log or configuration data is specified before it is processed by the agent.

f5-troubleshoot