ecosystem-mobile
Warn
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The file
scripts/install_all.pyutilizes thesubprocess.runmethod to execute system commands (skills install [skill_name]). This allows the skill to perform administrative-level changes to the agent's toolkit. - [EXTERNAL_DOWNLOADS]: The installation routine triggered by the skill fetches ten external packages (such as
mobile-security-auditorandrelease-orchestrator), introducing numerous unverified third-party dependencies into the workspace. - [PROMPT_INJECTION]: The
SKILL.mdfile contains directive 'Execution Rules' and instructions that attempt to override the agent's default planning behavior, commanding it to 'actively guide' users toward installation and strictly forbidding it from attempting tasks autonomously.
Audit Metadata