iopho-analyzing-videos

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the python3 interpreter to run a local script (scripts/video_to_storyboard.py) and utilizes the ffmpeg utility for frame extraction tasks.- [EXTERNAL_DOWNLOADS]: Installs the google-generativeai package from the public registry via pip. This library is provided by a well-known and trusted technology company.- [PROMPT_INJECTION]: The skill presents a vulnerability surface for indirect prompt injection through the processing of untrusted video data.
  • Ingestion points: Video files are uploaded to and processed by the Gemini API (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content within the video data are defined.
  • Capability inventory: The skill can execute shell commands (python, ffmpeg, pip) and perform file system write operations.
  • Sanitization: No sanitization or validation of the input video content or the resulting model output is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 07:29 PM