ios-to-android
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code from an external path which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads source files from a user-specified iOS codebase directory in Step 1.
- Boundary markers: There are no instructions or delimiters defined to ensure the agent ignores embedded instructions within the source files during analysis.
- Capability inventory: The skill performing file reading, creation of new files in the target Android project (Step 5), and asset copying between directories (Step 6).
- Sanitization: The skill lacks validation or sanitization steps for the content of the source files before implementation.
Audit Metadata