skills/mukul975/anthropic-cybersecurity-skills/reverse-engineering-android-malware-with-jadx/Gen Agent Trust Hub
reverse-engineering-android-malware-with-jadx
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/agent.pyfile executes CLI tools (apktool,jadx) viasubprocess.run. The implementation uses list-based arguments and the defaultshell=Falsesetting, which prevents command injection vulnerabilities. - [PROMPT_INJECTION]: The skill processes untrusted APK files and extracts strings (URLs, IPs, code snippets) which are presented to the AI agent. This constitutes an Indirect Prompt Injection surface. * Ingestion points: Data is read from external APK files provided by the user in
scripts/agent.py. * Boundary markers: Extracted strings are included in the report output without delimiters or isolation instructions. * Capability inventory: The skill has the capability to execute shell commands and write to the filesystem via the analysis script. * Sanitization: No sanitization or escaping is performed on data extracted from the APK before it is displayed to the agent.
Audit Metadata