researching-competitor-ads
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to browse and analyze competitor landing pages and advertisements, which could contain malicious instructions designed to manipulate the agent's analysis or output.
- Ingestion points: Competitor websites, landing pages, and ad creatives (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters to help the agent distinguish between data to be analyzed and instructions to be followed.
- Capability inventory: The methodology involves "Creative Reconnaissance" and "Funnel Mapping," which imply the use of web browsing and data extraction capabilities.
- Sanitization: The instructions do not specify any validation, filtering, or sanitization of the content retrieved from external sources.
Audit Metadata