seo-technical
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for the agent to ingest and process dynamic data from external sources (such as product databases or blog content) to generate SEO metadata and structured data. If this source data is maliciously crafted, it could attempt to influence the agent's behavior.
- Ingestion points: External data is retrieved through functions like
getProduct(id)andgetPost(slug)as demonstrated inAGENTS.md. - Boundary markers: The provided examples do not use specific delimiters or instructions to ignore embedded commands within the dynamic metadata fields, which is characteristic of SEO implementation.
- Capability inventory: The skill examples in
AGENTS.mddemonstrate filesystem access viareadFile(for loading fonts), URL navigation viaredirect, and script injection into the browser DOM usingdangerouslySetInnerHTML. - Sanitization: The skill proactively addresses security in
AGENTS.mdby providing a sanitization pattern.replace(/</g, '\\u003c')to prevent script injection in JSON-LD structured data.
Audit Metadata