seo-internal-linking

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill follows its stated purpose of SEO auditing and requires user confirmation for any file modifications.\n- [COMMAND_EXECUTION]: The skill requests permission to write internal linking reports and modify site content files (Markdown/MDX). This capability is restricted to SEO improvements and is gated by user approval before changes are applied.\n- [PROMPT_INJECTION]: The skill uses subagents to explore and extract metadata from site content, presenting a surface for indirect prompt injection.\n
  • Ingestion points: Local site content files (Markdown/MDX) processed by subagents (SKILL.md).\n
  • Boundary markers: None identified in the prompt template for the exploration subagent.\n
  • Capability inventory: File read/write access and subagent dispatch via the Task tool (SKILL.md).\n
  • Sanitization: Content is processed as-is without specific sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:52 AM