The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of F5 administrative commands via a Python-based bridge ($MCP_CALL) and scripts defined by environment variables ($F5_MCP_SCRIPT). This is a standard architectural pattern for its intended purpose and provides a clear separation of concerns.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it retrieves and analyzes system logs that may contain attacker-controlled content.
Ingestion points: F5 system logs retrieved via the show_logs_tool as documented in SKILL.md.
Boundary markers: None identified in the provided troubleshooting workflows.
Capability inventory: The skill has high-impact capabilities including the update_tool, create_tool, and delete_tool for modifying F5 objects.
Sanitization: No explicit sanitization, filtering, or validation of the log content is described before the agent processes it for decision-making.

f5-troubleshoot