mobile-security-mobsf

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill provides bash commands for running a Docker container and using curl to interact with the MobSF API.
  • [EXTERNAL_DOWNLOADS] (LOW): The instructions suggest pulling the 'opensecurity/mobile-security-framework-mobsf' Docker image. While MobSF is a well-known industry tool, this is an external dependency from a source not explicitly in the trusted list.
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface (Category 8) detected in the reporting phase. 1. Ingestion points: 'mobsf-report.json' response from the API. 2. Boundary markers: None specified in the instructions to separate report data from agent instructions. 3. Capability inventory: The agent is tasked with parsing and summarizing the results into a table. 4. Sanitization: No sanitization or validation of the report content is mentioned, which could allow malicious metadata in an APK/IPA to influence the agent's summary output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM