nmap-service-detection
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of system commands via the nmap binary to perform network reconnaissance, including service fingerprinting, OS detection, and vulnerability scanning as documented in SKILL.md.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external network data which represents a surface for indirect prompt injection. 1. Ingestion points: User-supplied network targets, port ranges, and script names, as well as remote service data like banners and headers. 2. Boundary markers: Documentation explicitly mentions that all scans respect a CIDR allowlist and are audit-logged. 3. Capability inventory: The skill executes the nmap utility with various flags using a Python-based MCP wrapper. 4. Sanitization: The skill implements restriction of scan targets via a CIDR allowlist as noted in the Important Rules section.
Audit Metadata