seo-audit
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted website content when performing audits. 1. Ingestion points: Website source code retrieved via web_fetch or curl (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are defined for fetched data. 3. Capability inventory: The skill is restricted to information gathering and reporting; it does not utilize code execution or file-writing tools. 4. Sanitization: No explicit sanitization of the fetched web content is specified.
- [DATA_EXPOSURE]: The skill reads local context files such as .agents/product-marketing-context.md to gather business context. These files are non-sensitive and are used to tailor the audit recommendations.
Audit Metadata