mobile-insecure-storage

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the use of various command-line interface tools to perform security audits on mobile device environments.
  • Tools used: adb, apktool, sqlite3, java, frida, and objection.
  • These commands are used as intended for the primary purpose of mobile application security analysis.
  • [DYNAMIC_EXECUTION]: The skill utilizes dynamic instrumentation to inspect the runtime behavior of applications and the state of the mobile keychain.
  • Pattern: Employs frida for runtime code injection and objection for dynamic filesystem and keychain inspection.
  • These operations are confined to the target mobile application and are standard practice for this type of security auditing.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted external sources, such as mobile system logs and application sandbox files.
  • Ingestion points: SKILL.md (instructions to read data via adb logcat, shared_prefs/*.xml, and sqlite3 dumps).
  • Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the current methodology.
  • Capability inventory: The agent is granted the capability to execute shell commands to interact with the device and inspect files.
  • Sanitization: No explicit sanitization or filtering of the ingested log or database content is described.
  • [EXTERNAL_DOWNLOADS]: The skill references the OWASP Mobile Application Security (MAS) project as a source for its framework and methodology.
  • Source: https://mas.owasp.org/MASTG/.
  • This reference is to a well-known and trusted technology organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 11:59 AM