storyboard
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to construct a video storyboard that is passed as a direct argument to a shell command.\n
- Ingestion points: User-provided scene descriptions, image prompts, and
image_reference_urlsreferenced in SKILL.md.\n - Boundary markers: Absent; the skill does not use delimiters or specific instructions to ignore malicious directives embedded within the user-supplied content.\n
- Capability inventory: The skill executes the
astria videoCLI command using the constructed storyboard (SKILL.md).\n - Sanitization: Absent; although the skill performs translation to English, it does not include instructions to sanitize or escape shell metacharacters before the content is placed in the CLI command.\n- [COMMAND_EXECUTION]: The skill generates and executes a shell command using the
astria videoCLI tool. This command execution is the primary intended mechanism for fulfilling the storyboard generation request.
Audit Metadata