firewalld
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill describes using 'sudo firewall-cmd' and 'sudo nft' to manage the system firewall. These operations are required for the primary purpose of firewall administration and represent legitimate usage.
- [PROMPT_INJECTION]: The skill presents templates for firewall rules that ingest external inputs like IPs and ports, which represents an indirect prompt injection surface. Ingestion points: Numerous examples in SKILL.md and references/common-rules.md. Boundary markers: No markers or explicit instructions to ignore embedded instructions are present. Capability inventory: Execution of system commands for firewall configuration. Sanitization: No input validation or sanitization logic is provided in the documentation.
Audit Metadata