music-to-storyboard
Warn
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a shell command
python3 -m music_analyzer storyboard "<input_path>"where<input_path>is derived from user input. Although the path is wrapped in double quotes, this pattern is vulnerable to shell command injection if the underlying agent does not properly sanitize the input to prevent breakout characters like backticks or subshells. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (music files or JSON analysis results) which serves as the basis for generating storyboard descriptions.
- Ingestion points: The user-provided
<audio_file_or_analysis_json>parameter described inSKILL.md. - Boundary markers: None; the skill lacks explicit instructions to treat the ingested data solely as data or to ignore embedded natural language instructions.
- Capability inventory: Shell command execution (
python3 -m music_analyzer) and subsequent prompt generation for a storyboard generator. - Sanitization: There is no evidence of sanitization or validation of the analysis JSON content before it is used to construct the final storyboard output.
Audit Metadata