seo-competitor-pages
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from competitor websites, which introduces a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill accepts competitor URLs as input via the
argument-hintand instructions inSKILL.mdto verify feature claims from public sources. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded within the retrieved competitor content.
- Capability inventory: The skill leverages the agent's ability to browse external web content, extract structured data, and generate new files including
COMPARISON-PAGE.mdandcomparison-schema.json. - Sanitization: There are no instructions for sanitizing or filtering the content fetched from external competitor URLs before it is processed by the agent.
Audit Metadata