landing-page-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a pipeline to fetch and analyze content from arbitrary external landing pages, creating a surface for indirect instructions to enter the agent's context.
- Ingestion points: The
auditLandingPagefunction inSKILL.mdtakes a URL parameter and processes its content through technical, content, and CRO audit pipelines. - Boundary markers: The implementation lacks explicit boundary markers or instructions telling the agent to disregard embedded commands within the external content fetched from the target URL.
- Capability inventory: The skill uses the ingested data to generate prioritized recommendations, estimated Quality Score impacts, and conversion rate improvements, which could be skewed by malicious content.
- Sanitization: No sanitization, HTML stripping, or filtering logic is described for the content retrieved from the landing pages prior to analysis.
Audit Metadata