competition-android-hooking
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any hardcoded credentials, malicious remote code downloads, or unauthorized persistence mechanisms. It adheres to its stated purpose of assisting in security research within a controlled environment.
- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it is designed to analyze untrusted external data.
- Ingestion points: Untrusted data enters the agent context through APK manifests, extracted resources, SQLite databases, and decompiled code snippets (SKILL.md).
- Boundary markers: There are no explicit instructions to the agent to treat external content as data only or to use boundary markers for isolation.
- Capability inventory: The skill facilitates dynamic analysis actions including Frida hooking, JNI symbol tracing, and request replay based on the analyzed data.
- Sanitization: No sanitization or validation steps are prescribed for the contents of the processed APK files.
Audit Metadata