nmap

Warn

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the nmap system utility and local bash scripts (e.g., scripts/nmap/identify-ports.sh) to perform network reconnaissance, which allows for system-level command execution based on user-provided targets.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by ingesting and processing data from external network services. 1. Ingestion points: Network scan results including service banners, HTTP headers, and version strings. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided. 3. Capability inventory: Execution of nmap system commands and bash scripts. 4. Sanitization: No sanitization of external scan data is performed before it is presented to the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 12:16 PM