skills/agricidaniel/codex-seo/seo-geo/Gen Agent Trust Hub

seo-geo

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external URLs for the purpose of SEO and GEO analysis, which is a known attack surface for indirect instructions.
  • Ingestion points: The skill accepts a URL argument and instructs the agent to analyze the content of the target site, including headings, paragraph lengths, and structured data.
  • Boundary markers: The instructions do not include explicit delimiters or safety guardrails to ensure the agent ignores malicious instructions that might be embedded in the analyzed webpage's text or HTML comments.
  • Capability inventory: The skill utilizes tool integrations (DataForSEO MCP tools) to perform scraping and searches, and it performs local file operations (reading/writing to .seo-cache/).
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external URLs before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 07:39 AM
Security Audit — agent-trust-hub — seo-geo