gif-sticker-maker

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/convert_mp4_to_gif.py utilizes subprocess.run to execute the ffmpeg utility for video conversion. The implementation follows security best practices by passing arguments as a list rather than a shell string, effectively mitigating command injection risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user photos and text captions to populate prompt templates for image and video generation. The risk is minimized by the skill's workflow, which encourages the use of a predefined caption table in references/captions.md and limits custom captions to short, 1-3 word phrases.
  • Ingestion points: User photos via the --subject-ref flag and captions via template interpolation in scripts/minimax_image.py.
  • Boundary markers: Prompt templates in assets/ wrap dynamic inputs in descriptive context.
  • Capability inventory: File system access (writing output stickers), network access (MiniMax API), and subprocess execution (ffmpeg).
  • Sanitization: Arguments are handled via argparse and API interactions use standard JSON structures.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the official MiniMax API (api.minimax.io) to perform its core functions. These external requests are legitimate and necessary for the stated creative purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:24 AM
Security Audit — agent-trust-hub — gif-sticker-maker