seo-technical-sitemap

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a technical guidance template for SEO tasks. It provides instructions on sitemap protocols, field requirements, and architecture without incorporating executable scripts, network operations, or privileged commands.\n- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to gather site context from local project files.\n
  • Ingestion points: Reads site URL and architecture data from .claude/product-marketing-context.md, .cursor/product-marketing-context.md, and other project configuration files (e.g., site-pages-config.ts).\n
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the processed marketing or configuration files.\n
  • Capability inventory: The skill's capabilities are limited to the generation of structured text (XML) and configuration code. No subprocess, network, or file-system writing capabilities are defined in the skill.\n
  • Sanitization: There are no instructions for sanitizing or validating the data retrieved from external project files before it is processed by the agent into sitemap output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:40 PM