seo-local
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/gsc_query.py and scripts/ga4_report.py) to retrieve performance data from Google Search Console and Google Analytics when configured (Steps 8b and 8c). These scripts are intended for internal data processing within the SEO audit workflow.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from external websites and review platforms (Steps 4, 5, and 7).
- Ingestion points: External data enters via Firecrawl and WebFetch from targeted business domains and review URLs.
- Boundary markers: The instructions do not specify delimiters or warnings to ignore instructions embedded in the scraped HTML or prose.
- Capability inventory: The skill has file-writing capabilities for generating reports and CSVs, and performs network operations via the SE Ranking and Firecrawl APIs.
- Sanitization: No specific sanitization or validation of the ingested external content is described before the agent processes it for SEO metrics.
Audit Metadata