scunthorpe-check

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites and local repository files, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads page content, field labels, and source code from target URLs and local directories provided by the user.
  • Boundary markers: Explicit instructions are included to treat all ingested content as untrusted data and to ignore any instructions embedded within that text.
  • Capability inventory: The skill utilizes Playwright tools for browser automation (filling forms, clicking buttons, evaluating Javascript) and has read access to the local file system.
  • Sanitization: The skill mandates escaping control characters and truncating long strings from external sources before including them in reports.
  • [DYNAMIC_EXECUTION]: The skill provides a Javascript template used within the browser environment via mcp__playwright__browser_evaluate to inspect DOM element properties, check validation states, and simulate clipboard events.
  • [COMMAND_EXECUTION]: The skill automates web browser interactions, including navigating to external URLs and performing form submissions, to verify the behavior of live validation systems.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 12:23 PM