analyzing-android-malware-with-apktool

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs extracting hardcoded strings and producing a JSON report containing "Extracted strings and potential IOCs", which would require the LLM to output verbatim values (potential API keys, tokens, passwords) found in APKs.

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

• Third-party content exposure detected (high risk: 0.70). The required workflow ingests the user-supplied APK file’s contents (manifest strings, DEX strings, etc.) via AnalyzeAPK(apk_path) and dx.get_strings(), and those APKs are outsider-authored samples unless the operating user authored them, creating an indirect prompt-injection risk through extracted free text (URLs/IPs/base64) placed into the LLM context.