forms-inputs-checkout
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted external data which introduces a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill is designed to critique screenshots, wireframes, Figma descriptions, and HTML/CSS/React components provided by the user (described in
SKILL.mdunder 'When to use this skill'). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat external content as untrusted data or to ignore instructions embedded within that data.
- Capability inventory: The skill generates executable frontend code (HTML/JS/React) and utilizes a
question()tool to prompt users for further information based on the input data. - Sanitization: The skill lacks explicit sanitization or validation logic for the external code or metadata it processes before interpolating it into the agent's decision-making flow.
Audit Metadata