network-scan-nmap
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill is designed to execute the
nmapbinary with various flags. This is the primary intended behavior but grants the agent direct interaction with the network layer. - [EXTERNAL_DOWNLOADS] (LOW): The skill references external dependencies, specifically the system-level installation of
nmapand the Python libraryxmltodict, which may lead to unverified package installation during runtime. - [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted data from network targets.
- Ingestion points: Data returned from network hosts via
nmapstdout and XML result files (SKILL.md). - Boundary markers: Absent. There are no instructions to ignore or treat embedded instructions as data within the scan results.
- Capability inventory: Command execution (
nmap) and file system writes. - Sanitization: Absent. The agent parses and summarizes raw string output from the tool without validation or escaping.
Audit Metadata