macos-e2e-scaffold

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates a local shell script (scripts/run-uitests.sh) and uses chmod +x to make it executable. This script is a template provided to the user to facilitate running the generated tests via xcodebuild.
  • [DATA_EXFILTRATION]: The skill reads project configuration files and source code to perform its audit and generate suggestions. These operations are conducted entirely locally to identify UI components, with no network transmission or external data exfiltration detected.
  • [PROMPT_INJECTION]: The skill ingests data from the project's source code to generate identifier suggestions, creating a surface for indirect prompt injection. The skill mitigates this by presenting all suggestions in a table for user review and confirmation before applying any changes, and by sanitizing the extracted text into a standard format.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 07:17 AM
Security Audit — agent-trust-hub — macos-e2e-scaffold