crawl-diff
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface. The skill processes data from external websites which may contain instructions designed to influence the agent's behavior.
- Ingestion points: Data is ingested from external URLs provided via the
startUrlparameter in theseo_run_reporttool as described inSKILL.md. - Boundary markers: The documentation lacks specific instructions or delimiters to isolate the crawled web content from the agent's operational instructions.
- Capability inventory: The agent has access to SEO monitoring and reporting tools including
seo_list_reports,seo_describe_report, andseo_run_report. - Sanitization: No sanitization or filtering logic is specified for the content retrieved from external crawls.
Audit Metadata