skills/iuliandita/skills/kali-linux/Gen Agent Trust Hub

kali-linux

Warn

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill recommends and utilizes shell commands with sudo for administrative tasks, including disk writing (dd), partition formatting (mkfs), and mounting, particularly within instructions for creating persistent live USB media.
  • [COMMAND_EXECUTION]: The skill defines and encourages the execution of numerous shell commands for system inspection, package auditing, and hardware diagnostics on Kali Linux.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on processing untrusted system state data, such as log files and package metadata, which could be manipulated to influence the agent's behavior.
  • Ingestion points: issue-or-workflow argument and diagnostic outputs from tools like journalctl, findmnt, and dpkg in SKILL.md.
  • Boundary markers: None identified in the prompt templates for separating untrusted system data.
  • Capability inventory: Extensive system diagnostic commands and access to administrative tools.
  • Sanitization: No explicit sanitization or filtering of system command outputs before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 21, 2026, 08:19 AM
Security Audit — agent-trust-hub — kali-linux