helpmetest-visual-check

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of visiting external web pages.
  • Ingestion points: The skill takes a URL as input and uses the 'Go To' command to navigate to and ingest content from external websites.
  • Boundary markers: There are no boundary markers or instructions to the agent to disregard instructions that might be embedded within the websites it visits.
  • Capability inventory: The skill utilizes the 'mcp__helpmetest-*' toolset which includes capabilities to interact with the page via 'Click', 'Hover', 'Fill Text', and 'Press Keys'.
  • Sanitization: No sanitization or filtering is applied to the data retrieved from external URLs before the agent processes screenshots and page state.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 12:34 AM