pagination
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill requires the agent to audit and analyze content from external websites, which represents an indirect prompt injection surface.
- Ingestion points: The agent is instructed to process HTML and URL structures from target websites during SEO audits (
SKILL.md,references/rule.md). - Boundary markers: The instructions do not specify delimiters or explicit warnings for the agent to ignore instructions that might be embedded within the audited content.
- Capability inventory: The agent uses its platform tools (such as web browsing or HTTP requests) to fetch external data.
- Sanitization: No specific sanitization, filtering, or validation logic for the external content is described.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and best practices from established external sources.
- References include technical guidelines from Google Search Central and frontendchecklist.io to support the auditing process.
Audit Metadata