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 skill uses the subprocess.run function to invoke system utilities including ffmpeg and gifsicle for media conversion and image optimization tasks.
  • Evidence: The skill implements FfmpegGifConverter._run_ffmpeg in references/step-4-ffmpeg-video-to-gif-pipeline.md and _gifsicle_optimize in references/step-7-batch-processing-and-optimization.md.
  • The implementation passes arguments as a list and does not enable shell=True, which is a recommended practice to mitigate command injection risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts by interpolating them into API requests for AI image generators such as DALL-E and Stable Diffusion, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Prompts are ingested via the BatchItem.prompt and GenerationRequest.prompt dataclasses as shown in references/step-7-batch-processing-and-optimization.md and references/step-2-ai-image-generation-integration.md.
  • Boundary markers: The skill does not implement explicit delimiters or instruction-ignore markers when concatenating user input with internal style modifiers.
  • Capability inventory: The skill possesses capabilities for network operations via httpx, file system writes for outputting GIFs, and shell execution via subprocess.run for media processing.
  • Sanitization: No specific filtering or sanitization logic is applied to the input prompt strings prior to their use in API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:24 AM
Security Audit — agent-trust-hub — gif-sticker-maker