android-app-reverse

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly directs hooking and logging sensitive values (e.g., keys, IVs, SharedPreferences, Memory.readUtf8String) and producing validated code/requests, which requires capturing and outputting secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). Contains explicit, actionable techniques to bypass SSL pinning, intercept and log cryptographic keys/tokens (via Frida hooks), dump app code/native libs, modify and re-sign APKs, and install persistent system-level trust (Magisk/LSPosed) — all of which enable credential theft, data exfiltration and persistent bypasses; dual-use but high potential for abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's Stage 2 "流量捕获与 API 发现" explicitly instructs the agent to capture and read external app network traffic (commands like traffic_list, traffic_get_detail, traffic_read_body via android_proxy_mcp) and to analyze those untrusted third‑party responses to decide hooks and next actions, so third‑party content can directly influence behavior.