faq-page
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs its stated function of generating a UI component using standard HTML, CSS, and JavaScript. It does not attempt to access sensitive files, execute shell commands, or perform network operations outside of standard browser functionality.
- [PROMPT_INJECTION]: The skill exhibits a standard attack surface for indirect prompt injection as it processes external, untrusted data (a 'brief') to generate UI content. This is inherent to its generative purpose and the risk is mitigated by the limited capabilities of the output environment.
- Ingestion points: Data enters the agent context through the referenced 'DESIGN.md' and the user-provided 'brief' mentioned in the workflow.
- Boundary markers: The instructions do not define specific delimiters to isolate external input from the skill's core logic.
- Capability inventory: The skill is limited to generating client-side UI code within isolated artifacts; it has no access to subprocesses, sensitive file systems, or network exfiltration tools.
- Sanitization: There are no explicit instructions to sanitize or validate the content provided in the brief before it is used to generate the FAQ entries.
Audit Metadata