recipe-url-indexation-check
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
gmpCLI tool, specifically for inspecting URL status and retrieving sitemap information. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by interpolating user-supplied URLs directly into shell command arguments.
- Ingestion points: User-provided URLs and site domain strings used in Step 1 and Step 3.
- Boundary markers: The provided examples use double quotes around variables, which offers a basic level of shell escaping but remains dependent on the agent's underlying execution environment.
- Capability inventory: The skill requires and uses shell command execution via the
gmpbinary. - Sanitization: The skill does not include explicit validation or sanitization logic for the URL inputs before they are passed to the CLI.
Audit Metadata