search-console-setup
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to interact with external websites (Google Search Console, Bing Webmaster Tools, and the Cloudflare Dashboard) using browser automation tools. While these are official and highly trusted services, reading and parsing data from external web pages constitutes an indirect prompt injection surface.
- Ingestion points: The agent is instructed to navigate to and read settings from
search.google.com,bing.com, anddash.cloudflare.comto verify site ownership and configuration status (specificallySKILL.md). - Boundary markers: There are no explicit instructions to the agent to ignore or delimit potentially untrusted content encountered during the browser automation process.
- Capability inventory: The skill leverages the agent's ability to navigate browser tabs, read page content, and perform clicks to modify domain settings, such as Caching configuration and AI bot policies.
- Sanitization: The instructions do not define any validation or sanitization requirements for the data retrieved from the web interfaces before it is processed by the agent.
Audit Metadata