skills/marcfargas/skills/web-search/Gen Agent Trust Hub

web-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The search.js script executes the ddgs CLI using execFileSync. Arguments are passed as an array, which correctly mitigates shell injection risks.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill relies on the user manually installing the ddgs tool and NPM packages. These are standard external dependencies for web scraping and search tasks.
  • [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface. [1] Ingestion points: Untrusted content is fetched from arbitrary URLs in search.js and content.js. [2] Boundary markers: The output uses result headers (e.g., --- Result 1 ---) but lacks explicit instructions for the agent to ignore commands within the data. [3] Capability inventory: The skill can access the network and execute a local search binary. [4] Sanitization: The Readability library removes script and style tags, but it does not filter the extracted text for malicious natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM