Skills
skills/a5c-ai/babysitter/qt-installer-framework-config/Gen Agent Trust Hub

qt-installer-framework-config

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (MEDIUM): The skill is vulnerable to indirect prompt injection because it interpolates user-provided metadata directly into executable scripts and configuration files without sanitization.
  • Ingestion points: Metadata fields in the SKILL.md input schema, specifically appInfo.name, appInfo.publisher, and components[].displayName.
  • Boundary markers: None. The templates in SKILL.md show direct interpolation into XML and JavaScript (.qs) files.
  • Capability inventory: The skill possesses Write capabilities to create .qs (Qt Script) files and Bash capabilities to execute build tools like binarycreator.
  • Sanitization: No evidence of sanitization, escaping, or schema validation to prevent malicious injection into the generated JavaScript logic or XML structure.
  • COMMAND_EXECUTION (LOW): The skill uses the Bash tool to execute standard build utilities (binarycreator, repogen) and deployment tools (rsync). These operations are consistent with the skill's documented purpose.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:54 AM