keyword-clustering
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs keyword clustering and mapping using provided SEO tools. All tool invocations and workflows are consistent with the stated purpose.\n- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection due to processing external keyword and SERP data.\n
- Ingestion points: SKILL.md (via tools: list_saved_keywords, research_keywords, get_ranked_keywords, get_search_console_performance, get_serp_results, search_local_businesses)\n
- Boundary markers: Absent. No specific delimiters or safety instructions are defined to separate ingested data from agent instructions.\n
- Capability inventory: SKILL.md (save_keywords tool for updating keyword tags)\n
- Sanitization: Absent. No explicit validation logic is defined for the incoming keyword or search performance data.
Audit Metadata