wos-download

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill utilizes JavaScript blocks executed within the browser context to interact with the Document Object Model (DOM). These scripts are used to extract metadata (titles, DOIs, links) and to programmatically trigger file downloads by creating and clicking anchor elements.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites, including Web of Science and academic publisher pages. This creates a surface where the agent could potentially be influenced by content hosted on those external sites.\n
  • Ingestion points: Document content and link attributes extracted from external publisher URLs during the navigation steps in SKILL.md.\n
  • Boundary markers: The skill does not implement specific boundary markers or instructions to ignore commands potentially embedded in the academic papers or publisher pages.\n
  • Capability inventory: The skill possesses the capability to navigate to arbitrary URLs, execute JavaScript in the browser, interact with UI elements, and initiate file downloads.\n
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external sites before it is processed by the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 01:43 AM