seo-keywords

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill instructs the agent to execute shell commands using variables sourced from configuration files.
  • Ingestion points: Client configuration files located at .seo/clients/{slug}/config.json provide the {domain} and {slug} variables.
  • Boundary markers: No explicit sanitization or boundary markers are defined for the interpolated variables within the shell commands.
  • Capability inventory: The skill uses firecrawl (an external CLI tool) and wc via shell execution.
  • Sanitization: There is no evidence of input validation or escaping for the {domain} variable before it is passed to the shell.
  • Evidence: The instruction firecrawl map {domain} -o .seo/clients/{slug}/technical/sitemap-urls.txt in rules/client-setup.md demonstrates direct interpolation of data into a command-line interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 05:32 PM