multi-platform-apps-multi-platform
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) due to the interpolation of user-provided feature specifications into agent prompts.
- Ingestion points: The $ARGUMENTS variable is interpolated directly into prompts for subagents such as 'backend-architect', 'ui-ux-designer', and platform-specific developers in SKILL.md.
- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to isolate user-controlled input from the workflow's core instructions.
- Capability inventory: The skill possesses high-level capabilities including API contract design, multi-platform code implementation (Web, iOS, Android, Desktop), and test automation via the Task tool.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the $ARGUMENTS content before it is passed to the subagents.
Audit Metadata