brand-architecture
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of documentation guidelines and strategic templates. It contains no executable code, shell commands, or obfuscated content.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill attempts to read context from .agents/brand-context.md. This is a standard local configuration path within the agent's environment and does not involve accessing system-level sensitive files or exfiltrating data to external servers.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface. 1. Ingestion points: .agents/brand-context.md. 2. Boundary markers: Absent. 3. Capability inventory: No shell execution, file system modifications, or network operations are present. 4. Sanitization: Absent. Because the skill lacks any impactful capabilities, this ingestion point is evaluated as safe.
Audit Metadata