search-autocomplete
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a frontend component that ingests and renders search results from external providers like Algolia or Elasticsearch. This involves a data ingestion surface where external content is reflected in the UI.
- Ingestion points: The
SearchAutocomplete.jsxcomponent processes product and category data, including highlighted HTML snippets, from a backend search API endpoint. - Boundary markers: The UI logic restricts result display to queries with a minimum character length, though no specific prompt-level delimiters are used.
- Capability inventory: The skill utilizes
fetchfor network requests anddangerouslySetInnerHTMLfor rendering matched text highlights. - Sanitization: The implementation guide explicitly requires and demonstrates the use of
DOMPurify.sanitize()to sanitize server-provided HTML before it is rendered, which effectively mitigates cross-site scripting (XSS) and injection risks from the search index.
Audit Metadata