ui-ux-pro-max

Warn

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions require the agent to execute a local script (search.py) using arguments directly derived from user input (<keyword>). This pattern creates a potential for shell command injection if the input contains malicious shell characters.
  • [PRIVILEGE_ESCALATION]: Instructions in the skill include the use of sudo for system package management (apt install) to set up the Python environment on Linux-based systems.
  • [EXTERNAL_DOWNLOADS]: The skill manifest and installation instructions fetch content from a remote GitHub repository belonging to an unverified personal account (majiayu000).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied keywords and interpolates them into shell commands without explicit sanitization or boundary markers defined in the instructions.
  • Ingestion points: User requirement analysis phase (Step 1 in SKILL.md).
  • Boundary markers: None provided to isolate or escape user input within the command strings.
  • Capability inventory: Execution of Python scripts via shell commands.
  • Sanitization: No filtering or validation logic is specified for the <keyword> variable.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 23, 2026, 03:25 PM
Security Audit — agent-trust-hub — ui-ux-pro-max