Skills
skills/malue-ai/dazee-small/linux-notification/Gen Agent Trust Hub

linux-notification

Warn

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains installation instructions using sudo with package managers like apt, dnf, and pacman. This suggests the execution of commands with elevated administrative privileges to install system-level dependencies.\n- [PROMPT_INJECTION]: The skill handles notification messages, which creates a surface for indirect prompt injection if the agent processes untrusted data.\n
  • Ingestion points: Notification titles and messages specified in the SKILL.md usage examples.\n
  • Boundary markers: The skill does not implement delimiters or provide instructions for the agent to ignore embedded commands within the notification text.\n
  • Capability inventory: The skill utilizes the notify-send system utility via subprocess execution.\n
  • Sanitization: There is no evidence of sanitization, filtering, or shell-escaping for the strings passed to the notify-send command.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 04:19 PM