brand-product-context
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and uses a markdown template to organize information. It does not execute code, perform network requests to untrusted domains, or access sensitive system files.- [PROMPT_INJECTION]: The skill is designed to ingest data from external, untrusted sources such as websites, pitch decks, and marketing copy (SKILL.md workflow step 1). It lacks explicit instructions for the agent to ignore embedded commands within those sources, creating a surface for Indirect Prompt Injection (Category 8). However, the impact is low as the skill's capabilities are limited to writing a text-based context file.
Audit Metadata