seo-technical
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data including robots.txt files, sitemaps, and security headers during the audit process.
- Ingestion points: External website assets such as robots.txt, sitemaps, and page metadata are specifically targeted for analysis in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are provided to distinguish between agent instructions and untrusted data.
- Capability inventory: While the skill is markdown-only, it directs the agent to perform actions that involve reading from network-accessible resources.
- Sanitization: The instructions do not include any guidance on sanitizing or escaping the content retrieved from these external sources.
Audit Metadata