handdrawn-live-video-generator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and adapt user-provided descriptions for surreal video clips. It lacks boundary markers or instructions to ignore instructions embedded within user input, which could allow an attacker to influence the prompt generation process or the behavior of downstream tools through malicious data.
- Ingestion points: Processes user-supplied descriptions of live-action environments and animated subjects in SKILL.md.
- Boundary markers: Absent; the skill does not use delimiters to separate user data from instructions.
- Capability inventory: References the execution of a local Python script (
scripts/minimax_h3_prompt_validator.py) and integration with external adapters (minimax-h3,h3-prompt-writing). - Sanitization: Absent; there are no defined filters or validation rules for the user input within the skill instructions.
Audit Metadata