media-processing
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [EXTERNAL_DOWNLOADS]: The shell scripts
remove-background.shandbatch-remove-background.share designed to automatically install thermbg-clipackage from the NPM registry if it is missing from the system. Additionally, the RMBG tool is documented to download AI models fromunpkg.comduring its initial run. Both NPM and unpkg are recognized well-known services. - [COMMAND_EXECUTION]: The skill uses Python's
subprocess.runand shell scripts to execute media operations using binaries like FFmpeg and ImageMagick. The Python scripts utilize list-based argument passing for these calls, which prevents shell injection vulnerabilities. - [INDIRECT_PROMPT_INJECTION]: As a media processing utility, the skill ingests user-supplied files which could contain malicious metadata. While this represents an attack surface, the risk is mitigated by the use of robust system binaries and safe command construction.
- [METADATA_POISONING]: The skill repository includes a
.coveragefile, which is an SQLite database generated during testing. This file contains absolute file paths from the author's local development environment, which is a minor configuration oversight.
Audit Metadata