seo-audit

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because its core workflow involves the agent visiting and analyzing external, untrusted websites and URLs provided by users.
  • Ingestion points: Target URLs and domain names collected in Step 1 of the workflow.
  • Boundary markers: The skill does not provide specific instructions or delimiters for the agent to use when processing external site content to distinguish it from the agent's own instructions.
  • Capability inventory: The skill itself contains no executable code or scripts, but it leverages the agent's native browsing and data processing capabilities.
  • Sanitization: There are no instructions for sanitizing or filtering instructions that might be embedded in the HTML or metadata of the websites being audited.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:42 PM