infographic-item-creator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions and reference materials do not contain any patterns intended to bypass safety filters or override agent behavior.
- [DATA_EXPOSURE]: The skill interacts with local design files within the
src/designs/itemsdirectory to ensure consistency with existing patterns, which is appropriate for its stated purpose. No access to sensitive files or credentials was found. - [EXTERNAL_DOWNLOADS]: The technical specification supports the use of well-known libraries such as
d3,lodash-es,tinycolor2, andround-polygon. These are standard utilities in the web development ecosystem. - [REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by generating code based on user prompts; however, it mitigates risks by providing a strict technical framework, component list, and predefined code templates in
references/item-prompt.mdto guide the agent's output.
Audit Metadata