seo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Potential for Indirect Prompt Injection. * Ingestion points: External website content crawled by the agent (up to 500 pages) as described in SKILL.md. * Boundary markers: Absent. The instructions do not provide delimiters or specific guidance to the agent to disregard instructions found within the crawled HTML content. * Capability inventory: Execution of local scripts (scripts/fetch_page.py), spawning and delegation to sub-agents (seo-technical, seo-content, etc.), and writing report files (FULL-AUDIT-REPORT.md, ACTION-PLAN.md) to the filesystem. * Sanitization: Absent. There is no mention of sanitizing, escaping, or validating the content retrieved from external domains before processing.
  • [COMMAND_EXECUTION]: The skill process requires the execution of a local Python script 'scripts/fetch_page.py' to retrieve HTML from homepages. This script is referenced but not included in the provided skill files.
  • [EXTERNAL_DOWNLOADS]: The skill performs automated network operations to crawl external websites for audit purposes. It also mentions optional enrichment via DataForSEO tools, which involves fetching live SERP and backlink data from external providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:23 AM