to-android-probe-script
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates Android Frida instrumentation code based on user-provided 'runtime questions'. This creates a vulnerability surface where a malicious prompt could result in the generation of scripts that access or exfiltrate sensitive application data.
- Ingestion points: The user's 'requested runtime question' as described in
SKILL.md. - Boundary markers: Lacks explicit delimiters or 'ignore embedded instructions' warnings for the user-supplied input.
- Capability inventory: The generated scripts have extensive capabilities, including direct access to Java/Kotlin runtime methods, private fields, and UI interaction via the
AndroidExpandglobalThis.JavaAPIs (detailed inreferences/direct-frida-generation.md). - Sanitization: While the documentation suggests best practices for code structure and resource cleanup, it does not include explicit instructions for sanitizing or escaping the user's input before interpolation into the generated script logic.
Audit Metadata