dreamina-opencli-image2video
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function involves executing shell commands through the
opencli jimengtool suite, includinggenerate-image2video,history, andworkspacescommands. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it interpolates user-supplied text into the
generate-image2videocommand as a motion prompt. - Ingestion points: User-provided
<prompt>in thegenerate-image2videocommand (SKILL.md). - Boundary markers: The skill uses double quotes to enclose the prompt string but does not specify explicit sanitization or instructions for the agent to ignore potentially malicious embedded content within the prompt.
- Capability inventory: The skill utilizes shell command execution via the
openclitoolset. - Sanitization: No explicit sanitization or validation of the input prompt is described in the provided files.
Audit Metadata