The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external files to inform its response, which is a standard surface for indirect prompt injection if those files contain malicious instructions.\n
Ingestion points: The skill attempts to read brand.yaml, context.md, and .agents/brand-context.md from the local file system.\n
Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when interpolating this data into the prompt.\n
Capability inventory: The skill contains no dangerous capabilities such as file writing, network requests, or command execution; additionally, disable-model-invocation is set to true, preventing the use of external tools.\n
Sanitization: No validation or sanitization of the file content is performed before processing.

brand-guidelines