ai-brand-kit
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for analyzing and validating user-supplied content against brand standards. This creates a surface where an attacker could provide text containing instructions designed to override the agent's behavior.
- Ingestion points: Variable placeholders like
{TEXT_TO_CHECK}in the consistency checker templates inreferences/patterns.md. - Boundary markers: Templates use clear formatting and quotes, but do not include explicit instructions for the AI to ignore commands embedded within the variable data.
- Capability inventory: The templates are designed for text analysis and do not grant the agent access to sensitive tools, file system writing, or network operations.
- Sanitization: The skill does not prescribe specific methods for sanitizing or escaping the input data before it is interpolated into the prompt templates.
Audit Metadata