web-search
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches search result data from Jina AI's public search endpoint.
- [DATA_EXFILTRATION]: Transmits user-provided search queries to the Jina Search API to retrieve relevant information.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data from the web.
- Ingestion points: Data is fetched from the Jina Search API in search.py.
- Boundary markers: The skill does not use specific delimiters or instructions to isolate retrieved content from agent instructions.
- Capability inventory: The script performs HTTP requests and outputs text to the console.
- Sanitization: The script does not perform sanitization or filtering on the text content received from the API.
Audit Metadata