brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as mission statements, values, and existing brand materials to generate a structured document. This data ingestion creates a surface for indirect prompt injection if the input materials contain hidden instructions meant to influence the agent's output or behavior.
- Ingestion points: The 'Process' section in SKILL.md instructs the agent to gather mission/values, audience, and personality data from external inputs.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to treat user-provided brand materials strictly as data rather than instructions.
- Capability inventory: The skill is limited to text generation; it does not request tools for file writing, network operations, or shell execution.
- Sanitization: No sanitization or validation logic is defined for the inputs used to generate the brand guidelines.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, binary files, or configuration files that execute code.
Audit Metadata