marketing-audit
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing external marketing content, such as landing pages, copy, and customer feedback, which are untrusted data sources.
- Ingestion points: The skill prompts the user for target URLs and product information in the 'Quick Start' and 'Phase 1: Status Quo' sections.
- Boundary markers: The instructions do not define clear delimiters or instruction-isolation patterns to prevent the agent from being influenced by malicious text embedded within the analyzed marketing materials.
- Capability inventory: The skill has the capability to trigger a wide range of secondary skills (e.g.,
lp-optimizer,seo-audit,analytics-tracking) based on the data it processes. - Sanitization: No methods for sanitizing or filtering external content are provided before the data is evaluated by the agent.
Audit Metadata