search-console-insights
Warn
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: MEDIUMPERSISTENCEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PERSISTENCE]: The skill includes
scripts/schedule_tracking.shwhich configures a macOSlaunchdLaunchAgent to perform weekly automated tracking. This mechanism allows the skill to run code periodically in the background to build rank history. - [INDIRECT_PROMPT_INJECTION]: The
scripts/geo_check.pyscript fetches responses from third-party AI assistants and renders them into an HTML report. While the script implements HTML entity escaping, it represents a surface where external, untrusted content is ingested into the agent's reporting context. - [COMMAND_EXECUTION]: Several scripts utilize the
subprocessmodule to interact with system tools such asgit(for checking repository status),gh(for viewing pull requests), andopen(for displaying reports). These operations are integrated into the skill's workflow for managing site analytics and applying SEO fix proposals.
Audit Metadata