jimeng-opencli-text2video
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
openclicommand-line tool, which is the primary mechanism for interacting with the Jimeng service for video generation and history retrieval. - [PROMPT_INJECTION]: The instructions include specific negative constraints, such as prohibiting the use of the
dreaminaCLI, to ensure the agent operates within the intended scope for standard members. - [PROMPT_INJECTION]: The skill possesses an indirect injection surface by passing user-provided prompts directly to shell commands.
- Ingestion points: The
<prompt>argument inopencli jimeng generate-video(SKILL.md). - Boundary markers: No specific delimiters or safety warnings are used to wrap the interpolated prompt.
- Capability inventory: Execution of shell commands via the
openclibinary (SKILL.md). - Sanitization: The instructions do not specify any sanitization or validation logic for the input prompt.
Audit Metadata