Network Ports Reference
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The skill provides numerous shell commands for active network reconnaissance and enumeration using tools like nmap, masscan, nikto, and gobuster. These instructions enable the agent to perform extensive probing of network services and hosts.
- [PROMPT_INJECTION] (HIGH): The skill creates a high-risk attack surface for indirect prompt injection. * Ingestion points: Data enters the agent context through network service banners, HTTP headers, and protocol-specific outputs retrieved during enumeration (e.g., via banner grabbing). * Boundary markers: Absent. The skill lacks delimiters or explicit instructions to ignore commands embedded in external service responses. * Capability inventory: The agent has a wide range of shell-based networking and reconnaissance tools available for execution. * Sanitization: Absent. There is no validation or escaping of external content before it is processed by the agent.
- [DATA_EXFILTRATION] (LOW): The skill initiates network operations to non-whitelisted target systems as part of its core scanning and service identification functionality.
Recommendations
- AI detected serious security threats
Audit Metadata