test-json-sql-search-web
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions to override behavior or bypass safety filters were detected.\n- Data Exposure & Exfiltration (SAFE): The skill performs public web searches and processes the results locally. No sensitive files or credentials are accessed.\n- Unverifiable Dependencies & Remote Code Execution (SAFE): No external packages or remote scripts are downloaded or executed.\n- Indirect Prompt Injection (LOW): The skill possesses a data ingestion surface via web search results. However, the lack of dangerous capabilities mitigates the risk.\n
- Ingestion points: plan.json (output of search-web step into $web_results).\n
- Boundary markers: Absent.\n
- Capability inventory: search-web, size, if, project, pluck, filter-structured, sort, say.\n
- Sanitization: Absent.
Audit Metadata