science-scrollytelling
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided scientific papers, datasets, or text documents to generate functional web application code. \n
- Ingestion points: User-provided research papers, datasets, and text documents. \n
- Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the scientific source material. \n
- Capability inventory: The agent has the capability to generate executable React, Tailwind CSS, and JavaScript code (using libraries like D3 or Recharts) based on the ingested content. \n
- Sanitization: No sanitization or validation steps are prescribed for the content extracted from external documents before it is used to generate the application structure and logic.
Audit Metadata