The Agent Skills Directory

[SAFE]: The skill is entirely instructional and serves as a knowledge base for marketing psychology. It contains no executable scripts, shell commands, or external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill reads data from .claude/product-marketing-context.md to tailor its output. While this represents a data ingestion surface, the skill lacks any dangerous capabilities (such as file writing, network access, or command execution) that could be exploited via indirect injection.
Ingestion points: .claude/product-marketing-context.md (read access mentioned in instructions).
Boundary markers: Absent; the agent is simply told to read the context.
Capability inventory: None; the skill's scope is limited to generating text-based marketing advice.
Sanitization: Absent; the content is used directly for contextual awareness.
[PROMPT_INJECTION]: There are no instructions attempting to override safety filters, extract system prompts, or bypass agent constraints. The role-play instructions are limited to the specific domain of marketing expertise.

marketing-psychology