ltx2
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of local scripts (e.g., tools/ltx2.py) and the Modal CLI to perform video generation and deployment tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts natural language prompts and image paths that are passed directly as command-line arguments, which could be exploited if the underlying scripts do not properly sanitize these inputs.
- Ingestion points: The --prompt and --input parameters used in shell commands within SKILL.md.
- Boundary markers: No delimiters or boundary markers are suggested for isolating user-supplied content.
- Capability inventory: The skill utilizes shell execution and remote deployment capabilities.
- Sanitization: There is no evidence of input sanitization or validation in the skill description.
- [EXTERNAL_DOWNLOADS]: The skill initiates the download of large model weights from HuggingFace during deployment; however, these are from a well-known service and are expected for the skill's purpose.
Audit Metadata