reversing-unity-il2cpp
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, deceptive metadata, or security risks were detected. The skill provides legitimate procedural guidance for mobile application security assessments.
- [COMMAND_EXECUTION]: The skill instructs the use of local command-line tools (unzip, rg, strings) and specialized binaries (Il2CppDumper, ilspycmd, frida) to process application files. This behavior is expected and appropriate for the skill's stated purpose of reverse engineering.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted binary data from external files. 1. Ingestion points: target.apk, libil2cpp.so, and global-metadata.dat mentioned in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file extraction, regex searching, binary metadata dumping, and dynamic process instrumentation. 4. Sanitization: Absent. This risk is inherent to the skill's primary function and is considered safe in this context as it processes binary artifacts rather than natural language instructions.
Audit Metadata