scanning-tools

Warn

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous shell commands for network discovery, vulnerability scanning, and wireless auditing. Several of these commands require superuser privileges (using sudo) to interact with raw network sockets or hardware interfaces. It also includes the generation of compliance remediation scripts.
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to install security tools using standard package managers like pip (for Prowler and ScoutSuite) and apt, and it utilizes official Docker images for web application scanning.
  • [PROMPT_INJECTION]: The skill processes user-supplied targets (IP addresses, hostnames) and incorporates them into executable commands. It mitigates this risk through a mandatory confirmation gate that requires the agent to verify target authorization and display the final command to the user.
  • Ingestion points: User-provided target URLs, IP addresses, and resource identifiers (SKILL.md).
  • Boundary markers: A four-step mandatory confirmation gate requiring target statement, authorization confirmation, command preview, and explicit user consent (SKILL.md).
  • Capability inventory: Extensive shell execution capabilities including network scanning (Nmap, Masscan), vulnerability assessment (Nessus, OpenVAS), and wireless testing (Aircrack-ng).
  • Sanitization: Relies on a manual human-in-the-loop review process where the agent must explain the command's effect and display the full syntax before execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 07:55 AM
Security Audit — agent-trust-hub — scanning-tools