seo-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and reason over untrusted external data, such as website URLs and pasted HTML, to perform SEO audits and planning.
- Ingestion points: Step 1 in
SKILL.mdexplicitly instructs the agent to gather target URLs and pasted HTML content for analysis. - Boundary markers: The skill requires findings to be labeled as 'measured' or 'inferred' and mandates a final pass through an
seo-quality-gatesskill, providing a level of logical boundary, though no explicit prompt delimiters (like XML tags) for the untrusted content are specified. - Capability inventory: The orchestrator dispatches instructions and project context to other specialized skills including technical auditing, content brief generation, and schema building.
- Sanitization: There is no mention of sanitizing, escaping, or filtering the ingested HTML content before it is processed by the LLM context.
Audit Metadata