brand-context
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill behavior is consistent with its stated purpose of managing brand identity data. It performs routine file read and write operations on local configuration files and does not attempt any suspicious network or system-level activities.
- [COMMAND_EXECUTION]: The skill mentions the use of a local script
scripts/brand.shto update brand configuration keys. This is a standard project-specific automation pattern and does not involve remote code execution or untrusted sources. - [INDIRECT_PROMPT_INJECTION]: The skill reads existing configuration data from the filesystem which represents a potential attack surface. \n
- Ingestion points: Processes
brand.yaml,context.md, and legacy.agents/brand-context.mdfrom the local workspace. \n - Boundary markers: No explicit markers or 'ignore' instructions are provided when loading external file content. \n
- Capability inventory: The skill can write and edit local files and execute a local management script. \n
- Sanitization: No content validation or sanitization is performed on the data read from files before processing.
Audit Metadata