music-composer
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
compose_music.pyexecutes theffmpegbinary usingsubprocess.runto transcode synthesized audio into MP3 format. The implementation is secure, utilizing a list of arguments rather than a raw shell string to prevent command injection, and it resolves the binary path using the system'sPATHviashutil.which.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-providedstoryline.jsonfiles, which presents a surface for indirect prompt injection. 1. Ingestion points: Data is loaded incompose_music.pyusingjson.loads. 2. Boundary markers: The instructions do not include delimiters or warnings to ignore instructions within the JSON content. 3. Capability inventory: The skill can write multiple audio and metadata files and execute theffmpegcommand. 4. Sanitization: The script validates data types but does not sanitize free-text metadata fields liketitleorcommentthat are output to logs.\n- [SAFE]: The skill operates entirely locally and does not perform unauthorized network requests or access sensitive files. All external links, such as the repository atgithub.com/ellmos-ai/ai-media-editorand references to tools like FluidSynth, are to official and well-known resources consistent with the skill's purpose.
Audit Metadata