mobile-platform-interaction

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from mobile application manifests and security tool outputs, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through the outputs of apktool, drozer, adb shell, and iOS plist inspections.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data retrieved from external mobile apps.
  • Capability inventory: The skill instructs the use of powerful command-line tools including adb, drozer, apktool, and frida, which could be abused if the agent is misled by injected instructions in the analyzed data.
  • Sanitization: No sanitization, escaping, or validation steps are provided to handle the content extracted from external apps before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 05:34 PM
Security Audit — agent-trust-hub — mobile-platform-interaction