dreamina-opencli-text2video
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates for shell commands using the
opencliutility, incorporating user-supplied prompts directly into the command arguments.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text prompts and uses them in executable shell commands without defined sanitization or robust boundary markers.\n - Ingestion points: The
<prompt>argument ingenerate-videoandgenerate-image2videocommands inSKILL.md.\n - Boundary markers: Absent; the instructions use double quotes in examples, which are insufficient to prevent shell meta-character injection or instruction overrides.\n
- Capability inventory: Shell command execution via
openclifor remote service interaction and session management.\n - Sanitization: Absent; no instructions are provided for escaping input or validating prompts before they are passed to the CLI tool.
Audit Metadata