video-shortform
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a platform-specific binary via
node "$OD_BIN" media generateto process video creation requests. This is the intended functional behavior of the skill within its ecosystem. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by incorporating user-defined descriptions into a shell command line.
- Ingestion points: User prompts and project metadata are used to construct the
--promptargument for the generation command inSKILL.md. - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to encapsulate user input.
- Capability inventory: The skill possesses the ability to execute shell commands via a node subprocess.
- Sanitization: No explicit sanitization or escaping of the user-provided prompt is instructed before it is passed to the command line.
Audit Metadata