seo-aeo-schema-generator
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content such as page titles, descriptions, and FAQ answers which may originate from external web sources or other skills in an automated workflow.
- Ingestion points: The
page_dataobject inSKILL.mdaccepts arbitrary strings from external sources including URLs, titles, and descriptions. - Boundary markers: The agent uses local JSON templates in the
references/directory with{{placeholder}}markers to structure and isolate user-provided content. - Capability inventory: The skill's operations are restricted to text generation; it has no capabilities for subprocess execution, file system modification, or network requests.
- Sanitization: The instructions explicitly mandate the removal of HTML tags from input values and require validation of data formats, such as ISO 8601 for dates and absolute protocol-prefixed strings for URLs.
Audit Metadata