ads
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze external, untrusted content such as competitor advertisements and customer reviews using browser-based tools. This capability introduces a surface for indirect prompt injection, where an attacker might hide malicious instructions within the analyzed data. The skill mitigates this by providing specific defensive instructions to the agent to disregard any commands found within external data sources.
- [EXTERNAL_DOWNLOADS]: The skill links to external documentation and a marketing tool registry located at a personal GitHub repository (github.com/coreyhaines31/marketingskills). While these references are for configuration and guidance rather than direct code execution, the source is not included in the predefined trusted organization list.
Audit Metadata