mobile-ios-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from mobile application packages.
- Ingestion points: The agent reads content from
.ipaarchives,Info.plistfiles, and binary headers using tools likeotoolandclass-dump(SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded prompts within the processed files.
- Capability inventory: The skill utilizes powerful instrumentation and analysis tools including
frida,objection, andmobsf(SKILL.md). - Sanitization: No specific validation or sanitization routines for the content of the IPA or configuration files are provided, representing a standard attack surface for indirect prompt injection.
Audit Metadata