mobile-code-quality

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by analyzing mobile application source code, decompiled binaries (via apktool), and dependency manifests. It utilizes shell-based analysis capabilities such as semgrep, checksec, and adb to interact with this data. There are no boundary markers or sanitization procedures defined in the instructions to mitigate the risk of malicious instructions within the analyzed applications influencing the agent's behavior.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple command-line utilities for security analysis, including adb for interacting with mobile devices, apktool for binary decompilation, and checksec for native library hardening analysis.
  • [EXTERNAL_DOWNLOADS]: The skill references the use of the Mobile Security Framework (MobSF) through a Docker container from the opensecurity organization, which is a well-known service in the security community.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 05:34 PM
Security Audit — agent-trust-hub — mobile-code-quality