skills/hkuds/vibe-trading/web-reader/Gen Agent Trust Hub

web-reader

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits user-provided URLs to the Jina Reader service (r.jina.ai) for processing. The documentation provides clear guidance to avoid sending URLs containing credentials or private tokens to this external service.
  • [COMMAND_EXECUTION]: The skill identifies a fallback mechanism using bash and requests for scenarios where the primary tool is blocked.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data from the web.
  • Ingestion points: Arbitrary external URLs are processed into Markdown content.
  • Boundary markers: The instructions do not define delimiters to separate untrusted content from the agent's instructions.
  • Capability inventory: The agent has access to shell execution (bash) and network tools.
  • Sanitization: No sanitization of the retrieved Markdown is performed before it is added to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:24 PM
Security Audit — agent-trust-hub — web-reader