asc-shots-pipeline

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies extensively on executing shell commands to manage the iOS build and simulation lifecycle.
  • Evidence: Instructions include execution of xcodebuild, xcrun simctl, and the asc CLI tool for app deployment and interaction.
  • Parallel execution patterns utilize xargs and background shell processes to orchestrate multiple simulator instances simultaneously.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party Python package to handle screenshot framing.
  • Evidence: Explicit instruction to run pip install koubou==0.13.0 for deterministic framing output.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and acting upon untrusted local configuration data.
  • Ingestion points: The skill reads orchestration logic and app parameters from .asc/shots.settings.json and .asc/screenshots.json (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the configuration files are provided.
  • Capability inventory: The skill can execute arbitrary build commands via xcodebuild, manipulate simulator states via simctl, and perform network uploads to App Store Connect via the asc tool.
  • Sanitization: There is no evidence of validation or sanitization of the values provided in the JSON configuration files before they are interpolated into shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 09:26 AM
Security Audit — agent-trust-hub — asc-shots-pipeline