microlink-google

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process unstructured data from external Google services (Search, News, Scholar, etc.), which creates a surface for indirect prompt injection where malicious content embedded in search results or metadata could attempt to influence the agent's logic.\n
  • Ingestion points: Titles, descriptions, and HTML content retrieved from Google verticals through the @microlink/google library.\n
  • Boundary markers: The documentation does not specify the use of delimiters or explicit instructions for the agent to ignore embedded commands within the ingested data.\n
  • Capability inventory: The skill facilitates fetching remote content and structured data from the Microlink API.\n
  • Sanitization: No explicit sanitization or validation of the retrieved content is described within the skill's instructions.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the @microlink/google Node.js library, which is a vendor-provided package for interacting with the Microlink API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 05:41 PM