community-intent

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use a CLI tool named seo to describe and run reports (e.g., seo reports run community-intent). This involves executing commands with specific parameters to interact with the SEO data service.
  • [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it processes untrusted search query data from Google Search Console.
  • Ingestion points: Search queries are retrieved through the seo_run_report MCP tool and specified CLI commands in SKILL.md.
  • Boundary markers: No delimiters or safety instructions are defined to help the agent isolate query data from its operational instructions.
  • Capability inventory: The agent can execute CLI commands (seo) and is tasked with making content recommendations based on its analysis of the data.
  • Sanitization: The skill documentation does not mention sanitizing or validating the search query strings being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:36 PM
Security Audit — agent-trust-hub — community-intent