seo-audit

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and analyze untrusted data from external websites.
  • Ingestion points: Web content is retrieved via web_fetch or curl based on user-provided URLs to perform the SEO audit as described in SKILL.md.
  • Boundary markers: The instructions do not include specific delimiters or 'ignore embedded instructions' warnings for the data being processed.
  • Capability inventory: The skill leverages the agent's web-fetching and text-analysis capabilities to perform audits, though it does not include its own executable scripts.
  • Sanitization: There are no instructions for sanitizing or validating the fetched HTML content to prevent malicious instructions embedded in metadata or comments from influencing the agent's behavior.
  • [SAFE]: All external references (Google Search Console, PageSpeed Insights, Rich Results Test) are well-known, trusted services.
  • [SAFE]: The skill consists entirely of Markdown documentation and contains no executable scripts, hardcoded credentials, or obfuscated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:19 PM