The Agent Skills Directory

[SAFE]: The skill's primary purpose is narrative generation based on user-provided details and local context. All instructions are aligned with this creative task.
[DATA_EXPOSURE]: The skill instructs the agent to read .agents/brand-context.md. This is a standard local configuration file used for maintaining context within the agent's environment and does not involve accessing sensitive system credentials or exfiltrating data to external servers.
[PROMPT_INJECTION]: No patterns associated with bypassing safety guidelines, role-playing as restricted identities (DAN), or ignoring system instructions were detected.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data, but no exploitable capabilities.
Ingestion points: Reads project-specific context from .agents/brand-context.md and processes user-supplied information about brand history.
Boundary markers: Absent; the skill does not explicitly use delimiters to separate instructions from ingested data.
Capability inventory: None; the skill does not perform shell command execution, file writes, or network requests.
Sanitization: Absent; the skill assumes the data provided is for creative writing purposes.

brand-story