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

seo-sxo

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests untrusted data from external websites and search engine results.\n
  • Ingestion points: Web content fetched from target URLs using scripts/fetch_page.py and metadata extracted from Google SERP results.\n
  • Boundary markers: The instructions lack specific delimiters or explicit system instructions to ignore potential commands embedded in the external data.\n
  • Capability inventory: The skill utilizes tools for web searching, page fetching, and interaction with the DataForSEO API.\n
  • Sanitization: While the fetching script is described as SSRF-safe, there is no evidence of sanitization of the content itself to filter out malicious prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 08:38 AM
Security Audit — agent-trust-hub — seo-sxo