scenes-gathered-zine-live-flow-v1-0

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The orchestration script scripts/build_live_zip_and_import.py uses subprocess.run to execute internal logic and system tools.
  • It searches for the importer application using mdfind to ensure the correct tool is used.
  • It executes scripts/render_adaptive_flat_tear.py via the Python interpreter to generate animation frames.
  • It invokes the Swift interpreter to run scripts/pair_live_photo.swift for metadata processing.
  • It uses the macOS open command to pass the completed ZIP file to the bundled 实况照片导入器.app.
  • [COMMAND_EXECUTION]: The rendering script scripts/render_adaptive_flat_tear.py calls ffmpeg to encode individual images into a QuickTime MOV file.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of images and user-supplied coordinate strings.
  • Ingestion points: The --input image path and the --path-points string argument in scripts/build_live_zip_and_import.py.
  • Boundary markers: The coordinate strings lack explicit boundary delimiters, but the rendering engine applies strict parsing rules.
  • Capability inventory: The skill has the ability to write to the file system, execute local scripts and system binaries, and invoke external macOS applications.
  • Sanitization: In scripts/render_adaptive_flat_tear.py, the path-points string is split and each component is explicitly converted to a float, which effectively prevents command injection via that specific parameter.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:14 AM
Security Audit — agent-trust-hub — scenes-gathered-zine-live-flow-v1-0