jina-web-fetcher

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism to fetch data from external websites and feed it into the agent context, creating a surface for potential indirect prompt injection.
  • Ingestion points: Command-line examples utilize curl to fetch content from the r.jina.ai proxy.
  • Boundary markers: Not provided; the skill relies on the agent's default handling of tool output.
  • Capability inventory: The skill uses standard network operations (curl) to retrieve data.
  • Sanitization: No sanitization is performed by the skill; it retrieves raw or Markdown-converted content from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill demonstrates network requests to r.jina.ai, which is a well-known service for converting web content into a format optimized for AI agents. These operations are essential to the skill's primary functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:49 AM
Security Audit — agent-trust-hub — jina-web-fetcher