screenstudio-alt

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions describe the use of several local scripts and binaries, including polish.py, render.py, studio.py, and a Swift-based input logger. These tools are used to process video data and interact with the ffmpeg command-line utility for media encoding tasks.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external files, specifically video recordings (.mp4) and event logs (.jsonl), which represent an indirect ingestion surface for untrusted data.
  • Ingestion points: Local media files and structured event logs (in.events.jsonl) used as input for the polishing scripts.
  • Boundary markers: None identified in the skill documentation.
  • Capability inventory: The workflow involves file system access and the execution of subprocesses for video rendering and logging.
  • Sanitization: Not explicitly documented; the skill's safety depends on the input validation implemented within the local processing scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 11:36 AM
Security Audit — agent-trust-hub — screenstudio-alt