keyword-research

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill defines a standard workflow for SEO research and data processing without any hidden or malicious instructions.\n- [SAFE]: All operations are conducted via a restricted set of tools, ensuring that network and data operations are limited to the intended SEO service scope.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from search engine results and Search Console performance logs.\n
  • Ingestion points: Data enters the context via get_serp_results, get_search_console_performance, and research_keywords in SKILL.md.\n
  • Boundary markers: No explicit delimiters are used in the prompt instructions to separate external data from system instructions.\n
  • Capability inventory: The agent has permissions to save data to a database via save_keywords, which requires explicit user confirmation.\n
  • Sanitization: The instructions mandate manual filtering and normalization of search terms, providing a human-in-the-loop and logic-based check on external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 01:50 PM
Security Audit — agent-trust-hub — keyword-research