structured-scraping-riveter

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses inline Python commands to parse the vendor-specific configuration file (~/.gooseworks/credentials.json) and establish the necessary environment variables for authentication.
  • [EXTERNAL_DOWNLOADS]: It references the npx gooseworks login command for authentication, which involves downloading the vendor's official command-line tool from the npm registry.
  • [PROMPT_INJECTION]: As the skill is designed to scrape and process external web content, it inherently possesses a surface for indirect prompt injection.
  • Ingestion points: Content is retrieved from arbitrary URLs provided in the 'url' or 'urls' parameters.
  • Capability inventory: The skill uses curl to interact with the Gooseworks API and can invoke tools such as web_search and web_scrape based on the provided configuration.
  • Boundary markers: There are no explicit delimiters or safety instructions provided in the scraping prompts to distinguish between data and instructions.
  • Sanitization: No sanitization process for the external web content is described prior to its analysis by the extraction engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — structured-scraping-riveter