specialist-engineering-mobile-app-builder
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input by interpolating it directly into a sub-agent's system prompt.
- Ingestion points: The variable '{the user's question}' in SKILL.md is used to inject user-provided content into the sub-agent prompt.
- Boundary markers: Absent. There are no delimiters such as XML tags or triple quotes used to wrap the user input, nor are there instructions to ignore embedded commands.
- Capability inventory: The skill uses the 'Agent' tool to create sub-agents, but does not explicitly request file system or network access in the provided code.
- Sanitization: There is no evidence of input filtering, validation, or escaping of the user content before it is interpolated.
Audit Metadata