engineering-mobile-app-builder
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill structure creates a vulnerability surface by processing external user-defined mobile application requirements to guide agent actions and code generation.
- Ingestion points: Processes user-supplied application specifications, feature descriptions, and development requests.
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious embedded instructions within processed user data.
- Capability inventory: No executable scripts are included within the skill folder; however, the agent is expected to use standard development tools for file manipulation and command execution.
- Sanitization: No input validation or content sanitization is defined for incoming user requirements.
- [NO_CODE]: The skill consists of a metadata-rich markdown file containing natural language instructions and static code templates, but it ships with no executable shell or script files.
Audit Metadata