ffmpeg-image-processing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies extensively on executing shell commands via the FFmpeg utility to perform image operations. This includes complex filter chains and batch processing loops.
- [INDIRECT_PROMPT_INJECTION]: The skill provides shell command templates that interpolate filenames (e.g.,
input.jpg,logo.png, and shell variables like$file). This creates a vulnerability surface for command injection if the agent uses filenames originating from untrusted data sources. - Ingestion points: The skill is designed to process image files which may be provided by users or external systems.
- Boundary markers: The command templates do not include specific delimiters or warnings to ignore instructions embedded in filenames or metadata.
- Capability inventory: The skill uses subprocess execution (FFmpeg) and shell control structures (for loops).
- Sanitization: There is no explicit sanitization or escaping of filenames shown in the command templates, increasing the risk if the agent executes these directly in a shell environment.
Audit Metadata