f5-health-check
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically constructs shell commands to interact with the F5 BIG-IP API. These commands utilize environment variables such as $F5_MCP_SCRIPT and $MCP_CALL to locate and execute necessary bridge scripts. This pattern is central to the skill's operational design and relies on the security of the local execution environment.
- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface due to its analysis of system logs which may contain data from untrusted sources.
- Ingestion points: System logs are retrieved and processed via the
show_logs_toolin Steps 7 and 8 to identify errors and anomalies. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives to prevent the agent from being influenced by instructions embedded within the log text.
- Capability inventory: The agent has access to sensitive tools including
create_tool,update_tool, anddelete_tool, which can modify the configuration of virtual servers, pools, and iRules. - Sanitization: There is no documented process for sanitizing or validating log content before it is summarized by the agent.
Audit Metadata