ecosystem-mobile

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script located at scripts/install_all.py that uses subprocess.run to execute system commands. This script is intended to install a predefined list of mobile ecosystem skills (e.g., accessibility-enforcer, mobile-perf-auditor) using a local tool named skills. The command execution is restricted to this static list and is explicitly documented for the user.
  • [PROMPT_INJECTION]: The SKILL.md file contains high-priority instructions that direct the AI agent's behavior, such as 'MUST consult the workflows' and an 'Execution Rule' that forbids the agent from performing certain tasks itself. These instructions are designed to maintain the role of the orchestrator within the intended workflow and do not attempt to bypass safety filters or exfiltrate data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 10:51 PM