Skills
Navigate
skills/revitalb-port/skills-registry-demo/responsive-testing/Gen Agent Trust Hub

responsive-testing

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external data from web pages, which is a potential vector for indirect prompt injection.
  • Ingestion points: Data is brought into the agent's context through browser_snapshot and browser_take_screenshot after navigating to a target URL (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or warnings to prevent the agent from following instructions that might be embedded in the analyzed web pages.
  • Capability inventory: The skill utilizes browser tools (browser_navigate, browser_take_screenshot, browser_snapshot) to interact with potentially untrusted web content (SKILL.md).
  • Sanitization: No sanitization or filtering of the HTML/Aria-tree content is specified before the agent evaluates it for responsive layout issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 01:52 PM