character-creator
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted user input and interpolating it into multiple contexts.
- Ingestion points: User-provided character descriptions (e.g., '创建一个赛博朋克女黑客') are used to expand into detailed prompts and are directly embedded into HTML templates (
assets/templates/portrait.htmlandassets/templates/gallery.html). - Boundary markers: None. The skill does not use delimiters or instructions to the agent to ignore embedded commands within the user-provided data.
- Capability inventory: The skill uses
user-sora2-mcp / create_image_taskfor remote image generation via thefal-aimodel and performs local file writes to save generated HTML pages (character-portrait.html,character-gallery.html). - Sanitization: There is no evidence of HTML escaping or sanitization of the
{{CHARACTER_NAME}}or{{CHARACTER_DESCRIPTION}}placeholders. An attacker could potentially inject malicious HTML or scripts that would execute when the user opens the generated character pages in their browser.
Audit Metadata