seo-technical
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to audit external URLs and tech stacks provided by the user, which introduces a potential attack surface where malicious content on the target site could influence agent behavior.
- Ingestion points: User-supplied site URLs, Google Search Console data, and technical stack descriptions as defined in SKILL.md.
- Boundary markers: The workflow lacks explicit boundary markers or instructions for the agent to ignore embedded natural language instructions within the processed HTML or metadata.
- Capability inventory: The skill outlines comprehensive audit capabilities including crawlability checks, security header validation, and structured data analysis across multiple technical dimensions.
- Sanitization: There are no specified sanitization or validation mechanisms to filter or escape content retrieved from external domains before it is processed by the agent.
Audit Metadata