multi-source-web-researcher

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard terminal commands to locate input files (such as Excel workbooks) within the workspace to identify the scope of the research task.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests data from untrusted external sources including general web search results, arXiv abstracts, and PDF documents. This is a standard characteristic of research agents.
  • Ingestion points: External content retrieved through local-web_search, arxiv_local-search_papers, and pdf-tools-read_pdf_pages.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted external content from agent instructions.
  • Capability inventory: The skill has the ability to execute terminal commands and modify local files (e.g., updating Excel workbooks).
  • Sanitization: No automated sanitization or data validation processes are specified for the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:26 PM
Security Audit — agent-trust-hub — multi-source-web-researcher