mobile-app-developer
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected in the skill instructions.
- [NO_CODE]: The skill consists entirely of natural language instructions and development checklists without any scripts, executables, or command-line operations.
- [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to bypass AI safety guidelines or override system prompts.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external application requirements, it lacks any high-risk capabilities that could be exploited via malicious input.
- Ingestion points: 'Query context manager for app requirements' (SKILL.md)
- Boundary markers: Absent
- Capability inventory: None (No subprocess calls, network operations, or file-system writes)
- Sanitization: Absent
Audit Metadata