ios-e2e
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands to facilitate the development and testing workflow. This includes building the iOS application with xcodebuild, performing A/B testing with git and cp commands, and using ffmpeg and ffprobe within a Python script to analyze video recordings for visual glitches.
- [DYNAMIC_EXECUTION]: The skill utilizes the debugger-evaluate tool to execute a JavaScript hook script (scripts/sheet-hooks.js) within the React Native application's runtime. This script interacts with the React DevTools hook to monitor component states and override properties for testing purposes. Additionally, the skill provides a Python snippet for the agent to parse local crash reports (.ips files).
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources that could be influenced by a third party, such as build logs (/tmp/truesheet-xcodebuild.log), application logs via debugger-log-registry, and system-generated crash reports.
- Ingestion points: Build log files, application debug logs, and .ips crash reports.
- Boundary markers: No specific delimiters or safety instructions are defined to separate the content of these logs from the agent's instructions.
- Capability inventory: The agent has the ability to execute shell commands (xcodebuild, git, ffmpeg), write to the filesystem, and evaluate code in the application context.
- Sanitization: The instructions for parsing logs and crash reports do not specify any sanitization or validation of the input data.
Audit Metadata